More stories

  • in

    Using artificial intelligence to find anomalies hiding in massive datasets

    Identifying a malfunction in the nation’s power grid can be like trying to find a needle in an enormous haystack. Hundreds of thousands of interrelated sensors spread across the U.S. capture data on electric current, voltage, and other critical information in real time, often taking multiple recordings per second.

    Researchers at the MIT-IBM Watson AI Lab have devised a computationally efficient method that can automatically pinpoint anomalies in those data streams in real time. They demonstrated that their artificial intelligence method, which learns to model the interconnectedness of the power grid, is much better at detecting these glitches than some other popular techniques.

    Because the machine-learning model they developed does not require annotated data on power grid anomalies for training, it would be easier to apply in real-world situations where high-quality, labeled datasets are often hard to come by. The model is also flexible and can be applied to other situations where a vast number of interconnected sensors collect and report data, like traffic monitoring systems. It could, for example, identify traffic bottlenecks or reveal how traffic jams cascade.

    “In the case of a power grid, people have tried to capture the data using statistics and then define detection rules with domain knowledge to say that, for example, if the voltage surges by a certain percentage, then the grid operator should be alerted. Such rule-based systems, even empowered by statistical data analysis, require a lot of labor and expertise. We show that we can automate this process and also learn patterns from the data using advanced machine-learning techniques,” says senior author Jie Chen, a research staff member and manager of the MIT-IBM Watson AI Lab.

    The co-author is Enyan Dai, an MIT-IBM Watson AI Lab intern and graduate student at the Pennsylvania State University. This research will be presented at the International Conference on Learning Representations.

    Probing probabilities

    The researchers began by defining an anomaly as an event that has a low probability of occurring, like a sudden spike in voltage. They treat the power grid data as a probability distribution, so if they can estimate the probability densities, they can identify the low-density values in the dataset. Those data points which are least likely to occur correspond to anomalies.

    Estimating those probabilities is no easy task, especially since each sample captures multiple time series, and each time series is a set of multidimensional data points recorded over time. Plus, the sensors that capture all that data are conditional on one another, meaning they are connected in a certain configuration and one sensor can sometimes impact others.

    To learn the complex conditional probability distribution of the data, the researchers used a special type of deep-learning model called a normalizing flow, which is particularly effective at estimating the probability density of a sample.

    They augmented that normalizing flow model using a type of graph, known as a Bayesian network, which can learn the complex, causal relationship structure between different sensors. This graph structure enables the researchers to see patterns in the data and estimate anomalies more accurately, Chen explains.

    “The sensors are interacting with each other, and they have causal relationships and depend on each other. So, we have to be able to inject this dependency information into the way that we compute the probabilities,” he says.

    This Bayesian network factorizes, or breaks down, the joint probability of the multiple time series data into less complex, conditional probabilities that are much easier to parameterize, learn, and evaluate. This allows the researchers to estimate the likelihood of observing certain sensor readings, and to identify those readings that have a low probability of occurring, meaning they are anomalies.

    Their method is especially powerful because this complex graph structure does not need to be defined in advance — the model can learn the graph on its own, in an unsupervised manner.

    A powerful technique

    They tested this framework by seeing how well it could identify anomalies in power grid data, traffic data, and water system data. The datasets they used for testing contained anomalies that had been identified by humans, so the researchers were able to compare the anomalies their model identified with real glitches in each system.

    Their model outperformed all the baselines by detecting a higher percentage of true anomalies in each dataset.

    “For the baselines, a lot of them don’t incorporate graph structure. That perfectly corroborates our hypothesis. Figuring out the dependency relationships between the different nodes in the graph is definitely helping us,” Chen says.

    Their methodology is also flexible. Armed with a large, unlabeled dataset, they can tune the model to make effective anomaly predictions in other situations, like traffic patterns.

    Once the model is deployed, it would continue to learn from a steady stream of new sensor data, adapting to possible drift of the data distribution and maintaining accuracy over time, says Chen.

    Though this particular project is close to its end, he looks forward to applying the lessons he learned to other areas of deep-learning research, particularly on graphs.

    Chen and his colleagues could use this approach to develop models that map other complex, conditional relationships. They also want to explore how they can efficiently learn these models when the graphs become enormous, perhaps with millions or billions of interconnected nodes. And rather than finding anomalies, they could also use this approach to improve the accuracy of forecasts based on datasets or streamline other classification techniques.

    This work was funded by the MIT-IBM Watson AI Lab and the U.S. Department of Energy. More

  • in

    Deep-learning technique predicts clinical treatment outcomes

    When it comes to treatment strategies for critically ill patients, clinicians want to be able to consider all their options and timing of administration, and make the optimal decision for their patients. While clinician experience and study has helped them to be successful in this effort, not all patients are the same, and treatment decisions at this crucial time could mean the difference between patient improvement and quick deterioration. Therefore, it would be helpful for doctors to be able to take a patient’s previous known health status and received treatments and use that to predict that patient’s health outcome under different treatment scenarios, in order to pick the best path.

    Now, a deep-learning technique, called G-Net, from researchers at MIT and IBM provides a window into causal counterfactual prediction, affording physicians the opportunity to explore how a patient might fare under different treatment plans. The foundation of G-Net is the g-computation algorithm, a causal inference method that estimates the effect of dynamic exposures in the presence of measured confounding variables — ones that may influence both treatments and outcomes. Unlike previous implementations of the g-computation framework, which have used linear modeling approaches, G-Net uses recurrent neural networks (RNN), which have node connections that allow them to better model temporal sequences with complex and nonlinear dynamics, like those found in the physiological and clinical time series data. In this way, physicians can develop alternative plans based on patient history and test them before making a decision.

    “Our ultimate goal is to develop a machine learning technique that would allow doctors to explore various ‘What if’ scenarios and treatment options,” says Li-wei Lehman, MIT research scientist in the MIT Institute for Medical Engineering and Science and an MIT-IBM Watson AI Lab project lead. “A lot of work has been done in terms of deep learning for counterfactual prediction but [it’s] been focusing on a point exposure setting,” or a static, time-varying treatment strategy, which doesn’t allow for adjustment of treatments as patient history changes. However, her team’s new prediction approach provides for treatment plan flexibility and chances for treatment alteration over time as patient covariate history and past treatments change. “G-Net is the first deep-learning approach based on g-computation that can predict both the population-level and individual-level treatment effects under dynamic and time varying treatment strategies.”

    The research, which was recently published in the Proceedings of Machine Learning Research, was co-authored by Rui Li MEng ’20, Stephanie Hu MEng ’21, former MIT postdoc Mingyu Lu MD, graduate student Yuria Utsumi, IBM research staff member Prithwish Chakraborty, IBM Research director of Hybrid Cloud Services Daby Sow, IBM data scientist Piyush Madan, IBM research scientist Mohamed Ghalwash, and IBM research scientist Zach Shahn.

    Tracking disease progression

    To build, validate, and test G-Net’s predictive abilities, the researchers considered the circulatory system in septic patients in the ICU. During critical care, doctors need to make trade-offs and judgement calls, such as ensuring the organs are receiving adequate blood supply without overworking the heart. For this, they could give intravenous fluids to patients to increase blood pressure; however, too much can cause edema. Alternatively, physicians can administer vasopressors, which act to contract blood vessels and raise blood pressure.

    In order to mimic this and demonstrate G-Net’s proof-of-concept, the team used CVSim, a mechanistic model of a human cardiovascular system that’s governed by 28 input variables characterizing the system’s current state, such as arterial pressure, central venous pressure, total blood volume, and total peripheral resistance, and modified it to simulate various disease processes (e.g., sepsis or blood loss) and effects of interventions (e.g., fluids and vasopressors). The researchers used CVSim to generate observational patient data for training and for “ground truth” comparison against counterfactual prediction. In their G-Net architecture, the researchers ran two RNNs to handle and predict variables that are continuous, meaning they can take on a range of values, like blood pressure, and categorical variables, which have discrete values, like the presence or absence of pulmonary edema. The researchers simulated the health trajectories of thousands of “patients” exhibiting symptoms under one treatment regime, let’s say A, for 66 timesteps, and used them to train and validate their model.

    Testing G-Net’s prediction capability, the team generated two counterfactual datasets. Each contained roughly 1,000 known patient health trajectories, which were created from CVSim using the same “patient” condition as the starting point under treatment A. Then at timestep 33, treatment changed to plan B or C, depending on the dataset. The team then performed 100 prediction trajectories for each of these 1,000 patients, whose treatment and medical history was known up until timestep 33 when a new treatment was administered. In these cases, the prediction agreed well with the “ground-truth” observations for individual patients and averaged population-level trajectories.

    A cut above the rest

    Since the g-computation framework is flexible, the researchers wanted to examine G-Net’s prediction using different nonlinear models — in this case, long short-term memory (LSTM) models, which are a type of RNN that can learn from previous data patterns or sequences — against the more classical linear models and a multilayer perception model (MLP), a type of neural network that can make predictions using a nonlinear approach. Following a similar setup as before, the team found that the error between the known and predicted cases was smallest in the LSTM models compared to the others. Since G-Net is able to model the temporal patterns of the patient’s ICU history and past treatment, whereas a linear model and MLP cannot, it was better able to predict the patient’s outcome.

    The team also compared G-Net’s prediction in a static, time-varying treatment setting against two state-of-the-art deep-learning based counterfactual prediction approaches, a recurrent marginal structural network (rMSN) and a counterfactual recurrent neural network (CRN), as well as a linear model and an MLP. For this, they investigated a model for tumor growth under no treatment, radiation, chemotherapy, and both radiation and chemotherapy scenarios. “Imagine a scenario where there’s a patient with cancer, and an example of a static regime would be if you only give a fixed dosage of chemotherapy, radiation, or any kind of drug, and wait until the end of your trajectory,” comments Lu. For these investigations, the researchers generated simulated observational data using tumor volume as the primary influence dictating treatment plans and demonstrated that G-Net outperformed the other models. One potential reason could be because g-computation is known to be more statistically efficient than rMSN and CRN, when models are correctly specified.

    While G-Net has done well with simulated data, more needs to be done before it can be applied to real patients. Since neural networks can be thought of as “black boxes” for prediction results, the researchers are beginning to investigate the uncertainty in the model to help ensure safety. In contrast to these approaches that recommend an “optimal” treatment plan without any clinician involvement, “as a decision support tool, I believe that G-Net would be more interpretable, since the clinicians would input treatment strategies themselves,” says Lehman, and “G-Net will allow them to be able to explore different hypotheses.” Further, the team has moved on to using real data from ICU patients with sepsis, bringing it one step closer to implementation in hospitals.

    “I think it is pretty important and exciting for real-world applications,” says Hu. “It’d be helpful to have some way to predict whether or not a treatment might work or what the effects might be — a quicker iteration process for developing these hypotheses for what to try, before actually trying to implement them in in a years-long, potentially very involved and very invasive type of clinical trial.”

    This research was funded by the MIT-IBM Watson AI Lab. More

  • in

    Can machine-learning models overcome biased datasets?

    Artificial intelligence systems may be able to complete tasks quickly, but that doesn’t mean they always do so fairly. If the datasets used to train machine-learning models contain biased data, it is likely the system could exhibit that same bias when it makes decisions in practice.

    For instance, if a dataset contains mostly images of white men, then a facial-recognition model trained with these data may be less accurate for women or people with different skin tones.

    A group of researchers at MIT, in collaboration with researchers at Harvard University and Fujitsu Ltd., sought to understand when and how a machine-learning model is capable of overcoming this kind of dataset bias. They used an approach from neuroscience to study how training data affects whether an artificial neural network can learn to recognize objects it has not seen before. A neural network is a machine-learning model that mimics the human brain in the way it contains layers of interconnected nodes, or “neurons,” that process data.

    The new results show that diversity in training data has a major influence on whether a neural network is able to overcome bias, but at the same time dataset diversity can degrade the network’s performance. They also show that how a neural network is trained, and the specific types of neurons that emerge during the training process, can play a major role in whether it is able to overcome a biased dataset.

    “A neural network can overcome dataset bias, which is encouraging. But the main takeaway here is that we need to take into account data diversity. We need to stop thinking that if you just collect a ton of raw data, that is going to get you somewhere. We need to be very careful about how we design datasets in the first place,” says Xavier Boix, a research scientist in the Department of Brain and Cognitive Sciences (BCS) and the Center for Brains, Minds, and Machines (CBMM), and senior author of the paper.  

    Co-authors include former MIT graduate students Timothy Henry, Jamell Dozier, Helen Ho, Nishchal Bhandari, and Spandan Madan, a corresponding author who is currently pursuing a PhD at Harvard; Tomotake Sasaki, a former visiting scientist now a senior researcher at Fujitsu Research; Frédo Durand, a professor of electrical engineering and computer science at MIT and a member of the Computer Science and Artificial Intelligence Laboratory; and Hanspeter Pfister, the An Wang Professor of Computer Science at the Harvard School of Enginering and Applied Sciences. The research appears today in Nature Machine Intelligence.

    Thinking like a neuroscientist

    Boix and his colleagues approached the problem of dataset bias by thinking like neuroscientists. In neuroscience, Boix explains, it is common to use controlled datasets in experiments, meaning a dataset in which the researchers know as much as possible about the information it contains.

    The team built datasets that contained images of different objects in varied poses, and carefully controlled the combinations so some datasets had more diversity than others. In this case, a dataset had less diversity if it contains more images that show objects from only one viewpoint. A more diverse dataset had more images showing objects from multiple viewpoints. Each dataset contained the same number of images.

    The researchers used these carefully constructed datasets to train a neural network for image classification, and then studied how well it was able to identify objects from viewpoints the network did not see during training (known as an out-of-distribution combination). 

    For example, if researchers are training a model to classify cars in images, they want the model to learn what different cars look like. But if every Ford Thunderbird in the training dataset is shown from the front, when the trained model is given an image of a Ford Thunderbird shot from the side, it may misclassify it, even if it was trained on millions of car photos.

    The researchers found that if the dataset is more diverse — if more images show objects from different viewpoints — the network is better able to generalize to new images or viewpoints. Data diversity is key to overcoming bias, Boix says.

    “But it is not like more data diversity is always better; there is a tension here. When the neural network gets better at recognizing new things it hasn’t seen, then it will become harder for it to recognize things it has already seen,” he says.

    Testing training methods

    The researchers also studied methods for training the neural network.

    In machine learning, it is common to train a network to perform multiple tasks at the same time. The idea is that if a relationship exists between the tasks, the network will learn to perform each one better if it learns them together.

    But the researchers found the opposite to be true — a model trained separately for each task was able to overcome bias far better than a model trained for both tasks together.

    “The results were really striking. In fact, the first time we did this experiment, we thought it was a bug. It took us several weeks to realize it was a real result because it was so unexpected,” he says.

    They dove deeper inside the neural networks to understand why this occurs.

    They found that neuron specialization seems to play a major role. When the neural network is trained to recognize objects in images, it appears that two types of neurons emerge — one that specializes in recognizing the object category and another that specializes in recognizing the viewpoint.

    When the network is trained to perform tasks separately, those specialized neurons are more prominent, Boix explains. But if a network is trained to do both tasks simultaneously, some neurons become diluted and don’t specialize for one task. These unspecialized neurons are more likely to get confused, he says.

    “But the next question now is, how did these neurons get there? You train the neural network and they emerge from the learning process. No one told the network to include these types of neurons in its architecture. That is the fascinating thing,” he says.

    That is one area the researchers hope to explore with future work. They want to see if they can force a neural network to develop neurons with this specialization. They also want to apply their approach to more complex tasks, such as objects with complicated textures or varied illuminations.

    Boix is encouraged that a neural network can learn to overcome bias, and he is hopeful their work can inspire others to be more thoughtful about the datasets they are using in AI applications.

    This work was supported, in part, by the National Science Foundation, a Google Faculty Research Award, the Toyota Research Institute, the Center for Brains, Minds, and Machines, Fujitsu Research, and the MIT-Sensetime Alliance on Artificial Intelligence. More

  • in

    The downside of machine learning in health care

    While working toward her dissertation in computer science at MIT, Marzyeh Ghassemi wrote several papers on how machine-learning techniques from artificial intelligence could be applied to clinical data in order to predict patient outcomes. “It wasn’t until the end of my PhD work that one of my committee members asked: ‘Did you ever check to see how well your model worked across different groups of people?’”

    That question was eye-opening for Ghassemi, who had previously assessed the performance of models in aggregate, across all patients. Upon a closer look, she saw that models often worked differently — specifically worse — for populations including Black women, a revelation that took her by surprise. “I hadn’t made the connection beforehand that health disparities would translate directly to model disparities,” she says. “And given that I am a visible minority woman-identifying computer scientist at MIT, I am reasonably certain that many others weren’t aware of this either.”

    In a paper published Jan. 14 in the journal Patterns, Ghassemi — who earned her doctorate in 2017 and is now an assistant professor in the Department of Electrical Engineering and Computer Science and the MIT Institute for Medical Engineering and Science (IMES) — and her coauthor, Elaine Okanyene Nsoesie of Boston University, offer a cautionary note about the prospects for AI in medicine. “If used carefully, this technology could improve performance in health care and potentially reduce inequities,” Ghassemi says. “But if we’re not actually careful, technology could worsen care.”

    It all comes down to data, given that the AI tools in question train themselves by processing and analyzing vast quantities of data. But the data they are given are produced by humans, who are fallible and whose judgments may be clouded by the fact that they interact differently with patients depending on their age, gender, and race, without even knowing it.

    Furthermore, there is still great uncertainty about medical conditions themselves. “Doctors trained at the same medical school for 10 years can, and often do, disagree about a patient’s diagnosis,” Ghassemi says. That’s different from the applications where existing machine-learning algorithms excel — like object-recognition tasks — because practically everyone in the world will agree that a dog is, in fact, a dog.

    Machine-learning algorithms have also fared well in mastering games like chess and Go, where both the rules and the “win conditions” are clearly defined. Physicians, however, don’t always concur on the rules for treating patients, and even the win condition of being “healthy” is not widely agreed upon. “Doctors know what it means to be sick,” Ghassemi explains, “and we have the most data for people when they are sickest. But we don’t get much data from people when they are healthy because they’re less likely to see doctors then.”

    Even mechanical devices can contribute to flawed data and disparities in treatment. Pulse oximeters, for example, which have been calibrated predominately on light-skinned individuals, do not accurately measure blood oxygen levels for people with darker skin. And these deficiencies are most acute when oxygen levels are low — precisely when accurate readings are most urgent. Similarly, women face increased risks during “metal-on-metal” hip replacements, Ghassemi and Nsoesie write, “due in part to anatomic differences that aren’t taken into account in implant design.” Facts like these could be buried within the data fed to computer models whose output will be undermined as a result.

    Coming from computers, the product of machine-learning algorithms offers “the sheen of objectivity,” according to Ghassemi. But that can be deceptive and dangerous, because it’s harder to ferret out the faulty data supplied en masse to a computer than it is to discount the recommendations of a single possibly inept (and maybe even racist) doctor. “The problem is not machine learning itself,” she insists. “It’s people. Human caregivers generate bad data sometimes because they are not perfect.”

    Nevertheless, she still believes that machine learning can offer benefits in health care in terms of more efficient and fairer recommendations and practices. One key to realizing the promise of machine learning in health care is to improve the quality of data, which is no easy task. “Imagine if we could take data from doctors that have the best performance and share that with other doctors that have less training and experience,” Ghassemi says. “We really need to collect this data and audit it.”

    The challenge here is that the collection of data is not incentivized or rewarded, she notes. “It’s not easy to get a grant for that, or ask students to spend time on it. And data providers might say, ‘Why should I give my data out for free when I can sell it to a company for millions?’ But researchers should be able to access data without having to deal with questions like: ‘What paper will I get my name on in exchange for giving you access to data that sits at my institution?’

    “The only way to get better health care is to get better data,” Ghassemi says, “and the only way to get better data is to incentivize its release.”

    It’s not only a question of collecting data. There’s also the matter of who will collect it and vet it. Ghassemi recommends assembling diverse groups of researchers — clinicians, statisticians, medical ethicists, and computer scientists — to first gather diverse patient data and then “focus on developing fair and equitable improvements in health care that can be deployed in not just one advanced medical setting, but in a wide range of medical settings.”

    The objective of the Patterns paper is not to discourage technologists from bringing their expertise in machine learning to the medical world, she says. “They just need to be cognizant of the gaps that appear in treatment and other complexities that ought to be considered before giving their stamp of approval to a particular computer model.” More

  • in

    When should someone trust an AI assistant’s predictions?

    In a busy hospital, a radiologist is using an artificial intelligence system to help her diagnose medical conditions based on patients’ X-ray images. Using the AI system can help her make faster diagnoses, but how does she know when to trust the AI’s predictions?

    She doesn’t. Instead, she may rely on her expertise, a confidence level provided by the system itself, or an explanation of how the algorithm made its prediction — which may look convincing but still be wrong — to make an estimation.

    To help people better understand when to trust an AI “teammate,” MIT researchers created an onboarding technique that guides humans to develop a more accurate understanding of those situations in which a machine makes correct predictions and those in which it makes incorrect predictions.

    By showing people how the AI complements their abilities, the training technique could help humans make better decisions or come to conclusions faster when working with AI agents.

    “We propose a teaching phase where we gradually introduce the human to this AI model so they can, for themselves, see its weaknesses and strengths,” says Hussein Mozannar, a graduate student in the Social and Engineering Systems doctoral program within the Institute for Data, Systems, and Society (IDSS) who is also a researcher with the Clinical Machine Learning Group of the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Institute for Medical Engineering and Science. “We do this by mimicking the way the human will interact with the AI in practice, but we intervene to give them feedback to help them understand each interaction they are making with the AI.”

    Mozannar wrote the paper with Arvind Satyanarayan, an assistant professor of computer science who leads the Visualization Group in CSAIL; and senior author David Sontag, an associate professor of electrical engineering and computer science at MIT and leader of the Clinical Machine Learning Group. The research will be presented at the Association for the Advancement of Artificial Intelligence in February.

    Mental models

    This work focuses on the mental models humans build about others. If the radiologist is not sure about a case, she may ask a colleague who is an expert in a certain area. From past experience and her knowledge of this colleague, she has a mental model of his strengths and weaknesses that she uses to assess his advice.

    Humans build the same kinds of mental models when they interact with AI agents, so it is important those models are accurate, Mozannar says. Cognitive science suggests that humans make decisions for complex tasks by remembering past interactions and experiences. So, the researchers designed an onboarding process that provides representative examples of the human and AI working together, which serve as reference points the human can draw on in the future. They began by creating an algorithm that can identify examples that will best teach the human about the AI.

    “We first learn a human expert’s biases and strengths, using observations of their past decisions unguided by AI,” Mozannar says. “We combine our knowledge about the human with what we know about the AI to see where it will be helpful for the human to rely on the AI. Then we obtain cases where we know the human should rely on the AI and similar cases where the human should not rely on the AI.”

    The researchers tested their onboarding technique on a passage-based question answering task: The user receives a written passage and a question whose answer is contained in the passage. The user then has to answer the question and can click a button to “let the AI answer.” The user can’t see the AI answer in advance, however, requiring them to rely on their mental model of the AI. The onboarding process they developed begins by showing these examples to the user, who tries to make a prediction with the help of the AI system. The human may be right or wrong, and the AI may be right or wrong, but in either case, after solving the example, the user sees the correct answer and an explanation for why the AI chose its prediction. To help the user generalize from the example, two contrasting examples are shown that explain why the AI got it right or wrong.

    For instance, perhaps the training question asks which of two plants is native to more continents, based on a convoluted paragraph from a botany textbook. The human can answer on her own or let the AI system answer. Then, she sees two follow-up examples that help her get a better sense of the AI’s abilities. Perhaps the AI is wrong on a follow-up question about fruits but right on a question about geology. In each example, the words the system used to make its prediction are highlighted. Seeing the highlighted words helps the human understand the limits of the AI agent, explains Mozannar.

    To help the user retain what they have learned, the user then writes down the rule she infers from this teaching example, such as “This AI is not good at predicting flowers.” She can then refer to these rules later when working with the agent in practice. These rules also constitute a formalization of the user’s mental model of the AI.

    The impact of teaching

    The researchers tested this teaching technique with three groups of participants. One group went through the entire onboarding technique, another group did not receive the follow-up comparison examples, and the baseline group didn’t receive any teaching but could see the AI’s answer in advance.

    “The participants who received teaching did just as well as the participants who didn’t receive teaching but could see the AI’s answer. So, the conclusion there is they are able to simulate the AI’s answer as well as if they had seen it,” Mozannar says.

    The researchers dug deeper into the data to see the rules individual participants wrote. They found that almost 50 percent of the people who received training wrote accurate lessons of the AI’s abilities. Those who had accurate lessons were right on 63 percent of the examples, whereas those who didn’t have accurate lessons were right on 54 percent. And those who didn’t receive teaching but could see the AI answers were right on 57 percent of the questions.

    “When teaching is successful, it has a significant impact. That is the takeaway here. When we are able to teach participants effectively, they are able to do better than if you actually gave them the answer,” he says.

    But the results also show there is still a gap. Only 50 percent of those who were trained built accurate mental models of the AI, and even those who did were only right 63 percent of the time. Even though they learned accurate lessons, they didn’t always follow their own rules, Mozannar says.

    That is one question that leaves the researchers scratching their heads — even if people know the AI should be right, why won’t they listen to their own mental model? They want to explore this question in the future, as well as refine the onboarding process to reduce the amount of time it takes. They are also interested in running user studies with more complex AI models, particularly in health care settings.

    “When humans collaborate with other humans, we rely heavily on knowing what our collaborators’ strengths and weaknesses are — it helps us know when (and when not) to lean on the other person for assistance. I’m glad to see this research applying that principle to humans and AI,” says Carrie Cai, a staff research scientist in the People + AI Research and Responsible AI groups at Google, who was not involved with this research. “Teaching users about an AI’s strengths and weaknesses is essential to producing positive human-AI joint outcomes.” 

    This research was supported, in part, by the National Science Foundation. More

  • in

    The promise and pitfalls of artificial intelligence explored at TEDxMIT event

    Scientists, students, and community members came together last month to discuss the promise and pitfalls of artificial intelligence at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) for the fourth TEDxMIT event held at MIT. 

    Attendees were entertained and challenged as they explored “the good and bad of computing,” explained CSAIL Director Professor Daniela Rus, who organized the event with John Werner, an MIT fellow and managing director of Link Ventures; MIT sophomore Lucy Zhao; and grad student Jessica Karaguesian. “As you listen to the talks today,” Rus told the audience, “consider how our world is made better by AI, and also our intrinsic responsibilities for ensuring that the technology is deployed for the greater good.”

    Rus mentioned some new capabilities that could be enabled by AI: an automated personal assistant that could monitor your sleep phases and wake you at the optimal time, as well as on-body sensors that monitor everything from your posture to your digestive system. “Intelligent assistance can help empower and augment our lives. But these intriguing possibilities should only be pursued if we can simultaneously resolve the challenges that these technologies bring,” said Rus. 

    The next speaker, CSAIL principal investigator and professor of electrical engineering and computer science Manolis Kellis, started off by suggesting what sounded like an unattainable goal — using AI to “put an end to evolution as we know it.” Looking at it from a computer science perspective, he said, what we call evolution is basically a brute force search. “You’re just exploring all of the search space, creating billions of copies of every one of your programs, and just letting them fight against each other. This is just brutal. And it’s also completely slow. It took us billions of years to get here.” Might it be possible, he asked, to speed up evolution and make it less messy?

    The answer, Kellis said, is that we can do better, and that we’re already doing better: “We’re not killing people like Sparta used to, throwing the weaklings off the mountain. We are truly saving diversity.”

    Knowledge, moreover, is now being widely shared, passed on “horizontally” through accessible information sources, he noted, rather than “vertically,” from parent to offspring. “I would like to argue that competition in the human species has been replaced by collaboration. Despite having a fixed cognitive hardware, we have software upgrades that are enabled by culture, by the 20 years that our children spend in school to fill their brains with everything that humanity has learned, regardless of which family came up with it. This is the secret of our great acceleration” — the fact that human advancement in recent centuries has vastly out-clipped evolution’s sluggish pace.

    The next step, Kellis said, is to harness insights about evolution in order to combat an individual’s genetic susceptibility to disease. “Our current approach is simply insufficient,” he added. “We’re treating manifestations of disease, not the causes of disease.” A key element in his lab’s ambitious strategy to transform medicine is to identify “the causal pathways through which genetic predisposition manifests. It’s only by understanding these pathways that we can truly manipulate disease causation and reverse the disease circuitry.” 

    Kellis was followed by Aleksander Madry, MIT professor of electrical engineering and computer science and CSAIL principal investigator, who told the crowd, “progress in AI is happening, and it’s happening fast.” Computer programs can routinely beat humans in games like chess, poker, and Go. So should we be worried about AI surpassing humans? 

    Madry, for one, is not afraid — or at least not yet. And some of that reassurance stems from research that has led him to the following conclusion: Despite its considerable success, AI, especially in the form of machine learning, is lazy. “Think about being lazy as this kind of smart student who doesn’t really want to study for an exam. Instead, what he does is just study all the past years’ exams and just look for patterns. Instead of trying to actually learn, he just tries to pass the test. And this is exactly the same way in which current AI is lazy.”

    A machine-learning model might recognize grazing sheep, for instance, simply by picking out pictures that have green grass in them. If a model is trained to identify fish from photos of anglers proudly displaying their catches, Madry explained, “the model figures out that if there’s a human holding something in the picture, I will just classify it as a fish.” The consequences can be more serious for an AI model intended to pick out malignant tumors. If the model is trained on images containing rulers that indicate the size of tumors, the model may end up selecting only those photos that have rulers in them.

    This leads to Madry’s biggest concerns about AI in its present form. “AI is beating us now,” he noted. “But the way it does it [involves] a little bit of cheating.” He fears that we will apply AI “in some way in which this mismatch between what the model actually does versus what we think it does will have some catastrophic consequences.” People relying on AI, especially in potentially life-or-death situations, need to be much more mindful of its current limitations, Madry cautioned.

    There were 10 speakers altogether, and the last to take the stage was MIT associate professor of electrical engineering and computer science and CSAIL principal investigator Marzyeh Ghassemi, who laid out her vision for how AI could best contribute to general health and well-being. But in order for that to happen, its models must be trained on accurate, diverse, and unbiased medical data.

    It’s important to focus on the data, Ghassemi stressed, because these models are learning from us. “Since our data is human-generated … a neural network is learning how to practice from a doctor. But doctors are human, and humans make mistakes. And if a human makes a mistake, and we train an AI from that, the AI will, too. Garbage in, garbage out. But it’s not like the garbage is distributed equally.”

    She pointed out that many subgroups receive worse care from medical practitioners, and members of these subgroups die from certain conditions at disproportionately high rates. This is an area, Ghassemi said, “where AI can actually help. This is something we can fix.” Her group is developing machine-learning models that are robust, private, and fair. What’s holding them back is neither algorithms nor GPUs. It’s data. Once we collect reliable data from diverse sources, Ghassemi added, we might start reaping the benefits that AI can bring to the realm of health care.

    In addition to CSAIL speakers, there were talks from members across MIT’s Institute for Data, Systems, and Society; the MIT Mobility Initiative; the MIT Media Lab; and the SENSEable City Lab.

    The proceedings concluded on that hopeful note. Rus and Werner then thanked everyone for coming. “Please continue to reflect about the good and bad of computing,” Rus urged. “And we look forward to seeing you back here in May for the next TEDxMIT event.”

    The exact theme of the spring 2022 gathering will have something to do with “superpowers.” But — if December’s mind-bending presentations were any indication — the May offering is almost certain to give its attendees plenty to think about. And maybe provide the inspiration for a startup or two. More

  • in

    Physics and the machine-learning “black box”

    Machine-learning algorithms are often referred to as a “black box.” Once data are put into an algorithm, it’s not always known exactly how the algorithm arrives at its prediction. This can be particularly frustrating when things go wrong. A new mechanical engineering (MechE) course at MIT teaches students how to tackle the “black box” problem, through a combination of data science and physics-based engineering.

    In class 2.C161 (Physical Systems Modeling and Design Using Machine Learning), Professor George Barbastathis demonstrates how mechanical engineers can use their unique knowledge of physical systems to keep algorithms in check and develop more accurate predictions.

    “I wanted to take 2.C161 because machine-learning models are usually a “black box,” but this class taught us how to construct a system model that is informed by physics so we can peek inside,” explains Crystal Owens, a mechanical engineering graduate student who took the course in spring 2021.

    As chair of the Committee on the Strategic Integration of Data Science into Mechanical Engineering, Barbastathis has had many conversations with mechanical engineering students, researchers, and faculty to better understand the challenges and successes they’ve had using machine learning in their work.

    “One comment we heard frequently was that these colleagues can see the value of data science methods for problems they are facing in their mechanical engineering-centric research; yet they are lacking the tools to make the most out of it,” says Barbastathis. “Mechanical, civil, electrical, and other types of engineers want a fundamental understanding of data principles without having to convert themselves to being full-time data scientists or AI researchers.”

    Additionally, as mechanical engineering students move on from MIT to their careers, many will need to manage data scientists on their teams someday. Barbastathis hopes to set these students up for success with class 2.C161.

    Bridging MechE and the MIT Schwartzman College of Computing

    Class 2.C161 is part of the MIT Schwartzman College of Computing “Computing Core.” The goal of these classes is to connect data science and physics-based engineering disciplines, like mechanical engineering. Students take the course alongside 6.C402 (Modeling with Machine Learning: from Algorithms to Applications), taught by professors of electrical engineering and computer science Regina Barzilay and Tommi Jaakkola.

    The two classes are taught concurrently during the semester, exposing students to both fundamentals in machine learning and domain-specific applications in mechanical engineering.

    In 2.C161, Barbastathis highlights how complementary physics-based engineering and data science are. Physical laws present a number of ambiguities and unknowns, ranging from temperature and humidity to electromagnetic forces. Data science can be used to predict these physical phenomena. Meanwhile, having an understanding of physical systems helps ensure the resulting output of an algorithm is accurate and explainable.

    “What’s needed is a deeper combined understanding of the associated physical phenomena and the principles of data science, machine learning in particular, to close the gap,” adds Barbastathis. “By combining data with physical principles, the new revolution in physics-based engineering is relatively immune to the “black box” problem facing other types of machine learning.”

    Equipped with a working knowledge of machine-learning topics covered in class 6.C402 and a deeper understanding of how to pair data science with physics, students are charged with developing a final project that solves for an actual physical system.

    Developing solutions for real-world physical systems

    For their final project, students in 2.C161 are asked to identify a real-world problem that requires data science to address the ambiguity inherent in physical systems. After obtaining all relevant data, students are asked to select a machine-learning method, implement their chosen solution, and present and critique the results.

    Topics this past semester ranged from weather forecasting to the flow of gas in combustion engines, with two student teams drawing inspiration from the ongoing Covid-19 pandemic.

    Owens and her teammates, fellow graduate students Arun Krishnadas and Joshua David John Rathinaraj, set out to develop a model for the Covid-19 vaccine rollout.

    “We developed a method of combining a neural network with a susceptible-infected-recovered (SIR) epidemiological model to create a physics-informed prediction system for the spread of Covid-19 after vaccinations started,” explains Owens.

    The team accounted for various unknowns including population mobility, weather, and political climate. This combined approach resulted in a prediction of Covid-19’s spread during the vaccine rollout that was more reliable than using either the SIR model or a neural network alone.

    Another team, including graduate student Yiwen Hu, developed a model to predict mutation rates in Covid-19, a topic that became all too pertinent as the delta variant began its global spread.

    “We used machine learning to predict the time-series-based mutation rate of Covid-19, and then incorporated that as an independent parameter into the prediction of pandemic dynamics to see if it could help us better predict the trend of the Covid-19 pandemic,” says Hu.

    Hu, who had previously conducted research into how vibrations on coronavirus protein spikes affect infection rates, hopes to apply the physics-based machine-learning approaches he learned in 2.C161 to his research on de novo protein design.

    Whatever the physical system students addressed in their final projects, Barbastathis was careful to stress one unifying goal: the need to assess ethical implications in data science. While more traditional computing methods like face or voice recognition have proven to be rife with ethical issues, there is an opportunity to combine physical systems with machine learning in a fair, ethical way.

    “We must ensure that collection and use of data are carried out equitably and inclusively, respecting the diversity in our society and avoiding well-known problems that computer scientists in the past have run into,” says Barbastathis.

    Barbastathis hopes that by encouraging mechanical engineering students to be both ethics-literate and well-versed in data science, they can move on to develop reliable, ethically sound solutions and predictions for physical-based engineering challenges. More

  • in

    Meet the 2021-22 Accenture Fellows

    Launched in October of 2020, the MIT and Accenture Convergence Initiative for Industry and Technology underscores the ways in which industry and technology come together to spur innovation. The five-year initiative aims to achieve its mission through research, education, and fellowships. To that end, Accenture has once again awarded five annual fellowships to MIT graduate students working on research in industry and technology convergence who are underrepresented, including by race, ethnicity, and gender.

    This year’s Accenture Fellows work across disciplines including robotics, manufacturing, artificial intelligence, and biomedicine. Their research covers a wide array of subjects, including: advancing manufacturing through computational design, with the potential to benefit global vaccine production; designing low-energy robotics for both consumer electronics and the aerospace industry; developing robotics and machine learning systems that may aid the elderly in their homes; and creating ingestible biomedical devices that can help gather medical data from inside a patient’s body.

    Student nominations from each unit within the School of Engineering, as well as from the four other MIT schools and the MIT Schwarzman College of Computing, were invited as part of the application process. Five exceptional students were selected as fellows in the initiative’s second year.

    Xinming (Lily) Liu is a PhD student in operations research at MIT Sloan School of Management. Her work is focused on behavioral and data-driven operations for social good, incorporating human behaviors into traditional optimization models, designing incentives, and analyzing real-world data. Her current research looks at the convergence of social media, digital platforms, and agriculture, with particular attention to expanding technological equity and economic opportunity in developing countries. Liu earned her BS from Cornell University, with a double major in operations research and computer science.

    Caris Moses is a PhD student in electrical engineering and computer science specializing inartificial intelligence. Moses’ research focuses on using machine learning, optimization, and electromechanical engineering to build robotics systems that are robust, flexible, intelligent, and can learn on the job. The technology she is developing holds promise for industries including flexible, small-batch manufacturing; robots to assist the elderly in their households; and warehouse management and fulfillment. Moses earned her BS in mechanical engineering from Cornell University and her MS in computer science from Northeastern University.

    Sergio Rodriguez Aponte is a PhD student in biological engineering. He is working on the convergence of computational design and manufacturing practices, which have the potential to impact industries such as biopharmaceuticals, food, and wellness/nutrition. His current research aims to develop strategies for applying computational tools, such as multiscale modeling and machine learning, to the design and production of manufacturable and accessible vaccine candidates that could eventually be available globally. Rodriguez Aponte earned his BS in industrial biotechnology from the University of Puerto Rico at Mayaguez.

    Soumya Sudhakar SM ’20 is a PhD student in aeronautics and astronautics. Her work is focused on theco-design of new algorithms and integrated circuits for autonomous low-energy robotics that could have novel applications in aerospace and consumer electronics. Her contributions bring together the emerging robotics industry, integrated circuits industry, aerospace industry, and consumer electronics industry. Sudhakar earned her BSE in mechanical and aerospace engineering from Princeton University and her MS in aeronautics and astronautics from MIT.

    So-Yoon Yang is a PhD student in electrical engineering and computer science. Her work on the development of low-power, wireless, ingestible biomedical devices for health care is at the intersection of the medical device, integrated circuit, artificial intelligence, and pharmaceutical fields. Currently, the majority of wireless biomedical devices can only provide a limited range of medical data measured from outside the body. Ingestible devices hold promise for the next generation of personal health care because they do not require surgical implantation, can be useful for detecting physiological and pathophysiological signals, and can also function as therapeutic alternatives when treatment cannot be done externally. Yang earned her BS in electrical and computer engineering from Seoul National University in South Korea and her MS in electrical engineering from Caltech. More