Data

Subterms

    More stories

    • 138 Shares189 Views

      in Data Management & Statistics

      A new way for quantum computing systems to keep their cool

      by

      Heat causes errors in the qubits that are the building blocks of a quantum computer, so quantum systems are typically kept inside refrigerators that keep the temperature just above absolute zero (-459 degrees Fahrenheit).

      But quantum computers need to communicate with electronics outside the refrigerator, in a room-temperature environment. The metal cables that connect these electronics bring heat into the refrigerator, which has to work even harder and draw extra power to keep the system cold. Plus, more qubits require more cables, so the size of a quantum system is limited by how much heat the fridge can remove.

      To overcome this challenge, an interdisciplinary team of MIT researchers has developed a wireless communication system that enables a quantum computer to send and receive data to and from electronics outside the refrigerator using high-speed terahertz waves.

      A transceiver chip placed inside the fridge can receive and transmit data. Terahertz waves generated outside the refrigerator are beamed in through a glass window. Data encoded onto these waves can be received by the chip. That chip also acts as a mirror, delivering data from the qubits on the terahertz waves it reflects to their source.

      This reflection process also bounces back much of the power sent into the fridge, so the process generates only a minimal amount of heat. The contactless communication system consumes up to 10 times less power than systems with metal cables.

      “By having this reflection mode, you really save the power consumption inside the fridge and leave all those dirty jobs on the outside. While this is still just a preliminary prototype and we have some room to improve, even at this point, we have shown low power consumption inside the fridge that is already better than metallic cables. I believe this could be a way to build largescale quantum systems,” says senior author Ruonan Han, an associate professor in the Department of Electrical Engineering and Computer Sciences (EECS) who leads the Terahertz Integrated Electronics Group.

      Han and his team, with expertise in terahertz waves and electronic devices, joined forces with associate professor Dirk Englund and the Quantum Photonics Laboratory team, who provided quantum engineering expertise and joined in conducting the cryogenic experiments.

      Joining Han and Englund on the paper are first author and EECS graduate student Jinchen Wang; Mohamed Ibrahim PhD ’21; Isaac Harris, a graduate student in the Quantum Photonics Laboratory; Nathan M. Monroe PhD ’22; Wasiq Khan PhD ’22; and Xiang Yi, a former postdoc who is now a professor at the South China University of Technology. The paper will be presented at the International Solid-States Circuits Conference.

      Tiny mirrors

      The researchers’ square transceiver chip, measuring about 2 millimeters on each side, is placed on a quantum computer inside the refrigerator, which is called a cryostat because it maintains cryogenic temperatures. These super-cold temperatures don’t damage the chip; in fact, they enable it to run more efficiently than it would at room temperature.

      The chip sends and receives data from a terahertz wave source outside the cryostat using a passive communication process known as backscatter, which involves reflections. An array of antennas on top of the chip, each of which is only about 200 micrometers in size, act as tiny mirrors. These mirrors can be “turned on” to reflect waves or “turned off.”

      The terahertz wave generation source encodes data onto the waves it sends into the cryostat, and the antennas in their “off” state can receive those waves and the data they carry.

      When the tiny mirrors are turned on, they can be set so they either reflect a wave in its current form or invert its phase before bouncing it back. If the reflected wave has the same phase, that represents a 0, but if the phase is inverted, that represents a 1. Electronics outside the cryostat can interpret those binary signals to decode the data.

      “This backscatter technology is not new. For instance, RFIDs are based on backscatter communication. We borrow that idea and bring it into this very unique scenario, and I think this leads to a good combination of all these technologies,” Han says.

      Terahertz advantages

      The data are transmitted using high-speed terahertz waves, which are located on the electromagnetic spectrum between radio waves and infrared light.

      Because terahertz waves are much smaller than radio waves, the chip and its antennas can be smaller, too, which would make the device easier to manufacture at scale. Terahertz waves also have higher frequencies than radio waves, so they can transmit data much faster and move larger amounts of information.

      But because terahertz waves have lower frequencies than the light waves used in photonic systems, the terahertz waves carry less quantum noise, which leads to less interference with quantum processors.

      Importantly, the transceiver chip and terahertz link can be fully constructed with standard fabrication processes on a CMOS chip, so they can be integrated into many current systems and techniques.

      “CMOS compatibility is important. For example, one terahertz link could deliver a large amount of data and feed it to another cryo-CMOS controller, which can split the signal to control multiple qubits simultaneously, so we can reduce the quantity of RF cables dramatically. This is very promising.” Wang says.

      The researchers were able to transmit data at 4 gigabits per second with their prototype, but Han says the sky is nearly the limit when it comes to boosting that speed. The downlink of the contactless system posed about 10 times less heat load than a system with metallic cables, and the temperature of the cryostat fluctuated up to a few millidegrees during experiments.

      Now that the researchers have demonstrated this wireless technology, they want to improve the system’s speed and efficiency using special terahertz fibers, which are only a few hundred micrometers wide. Han’s group has shown that these plastic wires can transmit data at a rate of 100 gigabits per second and have much better thermal insulation than fatter, metal cables.

      The researchers also want to refine the design of their transceiver to improve scalability and continue boosting its energy efficiency. Generating terahertz waves requires a lot of power, but Han’s group is studying more efficient methods that utilize low-cost chips. Incorporating this technology into the system could make the device more cost-effective.

      The transceiver chip was fabricated through the Intel University Shuttle Program. More

    • 113 Shares109 Views

      in Data Management & Statistics

      New chip for mobile devices knocks out unwanted signals

      by

      Imagine sitting in a packed stadium for a pivotal football game — tens of thousands of people are using mobile phones at the same time, perhaps video chatting with friends or posting photos on social media. The radio frequency signals being sent and received by all these devices could cause interference, which slows device performance and drains batteries.

      Designing devices that can efficiently block unwanted signals is no easy task, especially as 5G networks become more universal and future generations of wireless communication systems are developed. Conventional techniques utilize many filters to block a range of signals, but filters are bulky, expensive, and drive up production costs.

      MIT researchers have developed a circuit architecture that targets and blocks unwanted signals at a receiver’s input without hurting its performance. They borrowed a technique from digital signal processing and used a few tricks that enable it to work effectively in a radio frequency system across a wide frequency range.

      Their receiver blocked even high-power unwanted signals without introducing more noise, or inaccuracies, into the signal processing operations. The chip, which performed about 40 times better than other wideband receivers at blocking a special type of interference, does not require any additional hardware or circuitry. This would make the chip easier to manufacture at scale.

      “We are interested in developing electronic circuits and systems that meet the demands of 5G and future generations of wireless communication systems. In designing our circuits, we look for inspirations from other domains, such as digital signal processing and applied electromagnetics. We believe in circuit elegance and simplicity and try to come up with multifunctional hardware that doesn’t require additional power and chip area,” says senior author Negar Reiskarimian, the X-Window Consortium Career Development Assistant Professor in the Department of Electrical Engineering and Computer Science (EECS) and a core faculty member of the Microsystems Technology Laboratories.

      Reiskarimian wrote the paper with EECS graduate students Soroush Araei, who is the lead author, and Shahabeddin Mohin. The work is being presented at the International Solid-States Circuits Conference.

      Harmonic interference

      The researchers developed the receiver chip using what is known as a mixer-first architecture. This means that when a radio frequency signal is received by the device, it is immediately converted to a lower-frequency signal before being passed on to the analog-to-digital converter to extract the digital bits that it is carrying. This approach enables the radio to cover a wide frequency range while filtering out interference located close to the operation frequency.

      While effective, mixer-first receivers are susceptible to a particular kind of interference known as harmonic interference. Harmonic interference comes from signals that have frequencies which are multiples of a device’s operating frequency. For instance, if a device operates at 1 gigahertz, then signals at 2 gigahertz, 3 gigahertz, 5 gigahertz, etc., will cause harmonic interference. These harmonics can be indistinguishable from the original signal during the frequency conversion process.    

      “A lot of other wideband receivers don’t do anything about the harmonics until it is time to see what the bits mean. They do it later in the chain, but this doesn’t work well if you have high-power signals at the harmonic frequencies. Instead, we want to remove harmonics as soon as possible to avoid losing information,” Araei says.

      To do this, the researchers were inspired by a concept from digital signal processing known as block digital filtering. They adapted this technique to the analog domain using capacitors, which hold electric charges. The capacitors are charged up at different times as the signal is received, then they are switched off so that charge can be held and used later for processing the data.  

      These capacitors can be connected to each other in various ways, including connecting them in parallel, which enables the capacitors to exchange the stored charges. While this technique can target harmonic interference, the process results in significant signal loss. Stacking capacitors is another possibility, but this method alone is not enough to provide harmonic resilience.

      Most radio receivers already use switched-capacitor circuits to perform frequency conversion. This frequency conversion circuitry can be combined with block filtering to target harmonic interference.

      A precise arrangement

      The researchers found that arranging capacitors in a specific layout, by connecting some of them in series and then performing charge sharing, enabled the device to block harmonic interference without losing any information.

      “People have used these techniques, charge sharing and capacitor stacking, separately before, but never together. We found that both techniques must be done simultaneously to get this benefit. Moreover, we have found out how to do this in a passive way within the mixer without using any additional hardware while maintaining signal integrity and keeping the costs down,” he says.

      They tested the device by simultaneously sending a desired signal and harmonic interference. Their chip was able to block harmonic signals effectively with only a slight reduction in signal strength. It was able to handle signals that were 40 times more powerful than previous, state-of-the-art wideband receivers. More

    • 100 Shares189 Views

      in Data Management & Statistics

      Democratizing education: Bringing MIT excellence to the masses

      by

      How do you quantify the value of education or measure success? For the team behind the MIT Institute for Data, Systems, and Society’s (IDSS) MicroMasters Program in Statistics and Data Science (SDS), providing over 1,000 individuals from around the globe with access to MIT-level programming feels like a pretty good place to start. 

      Thanks to the MIT-conceived MicroMasters-style format, SDS faculty director Professor Devavrat Shah and his colleagues have eliminated the physical restrictions created by a traditional brick-and-mortar education, allowing 1,178 learners and counting from 89 countries access to an MIT education.

      “Taking classes from a Nobel Prize winner doesn’t happen every day,” says Oscar Vele, a strategic development worker for the town of Cuenca, Ecuador. “My dream has always been to study at MIT. I knew it was not easy — now, through this program, my dream came true.”

      “With an online forum, in principle, admission is no longer the gate — the merit is a gate,” says Shah. “If you take a class that is MIT-level, and if you perform at MIT-level, then you should get MIT-level credentials.”

      The MM SDS program, delivered in collaboration with MIT Open Learning, plays a key role in the IDSS mission of advancing education in data science, and supports MIT’s overarching belief that everyone should be able to access a quality education no matter what their life circumstances may be.

      “Getting a program like this up and running to the point where it has credentials and credibility across the globe, is an important milestone for us,” says Shah. “Basically, for us, it says we are here to stay, and we are just getting started.”

      Since the program launched in 2018, Shah says he and his team have seen learners from all walks of life, from high-schoolers looking for a challenge to late-in-life learners looking to either evolve or refresh their knowledge.

      “Then there are individuals who want to prove to themselves that they can achieve serious knowledge and build a career,” Shah says. “Circumstances throughout their lives, whether it’s the country or socioeconomic conditions they’re born in, they have never had the opportunity to do something like this, and now they have an MIT-level education and credentials, which is a huge deal for them.”

      Many learners overcome challenges to complete the program, from financial hardships to balancing work, home life, and coursework, and finding private, internet-enabled space for learning — not to mention the added complications of a global pandemic. One Ukrainian learner even finished the program after fleeing her apartment for a bomb shelter.

      Remapping the way to a graduate degree

      For Diogo da Silva Branco Magalhaes, a 44-year-old lifelong learner, curiosity and the desire to evolve within his current profession brought him to the MicroMasters program. Having spent 15 years working in the public transport sector, da Silva Branco Magalhaes had a very specific challenge at the front of his mind: artificial intelligence.

      “It’s not science fiction; it’s already here,” he says. “Think about autonomous vehicles, on-demand transportation, mobility as a service — AI and data, in particular, are the driving force of a number of disruptions that will affect my industry.”

      When he signed up for the MicroMasters Program in Statistics and Data Science, da Silva Branco Magalhaes’ said he had no long-term plans, but was taking a first step. “I just wanted to have a first contact with this reality, understand the basics, and then let’s see how it goes,” he describes.

      Now, after earning his credentials in 2021, he finds himself a few weeks into an accelerated master’s program at Northwestern University, one of several graduate pathways supported by the MM SDS program.

      “I was really looking to gain some basic background knowledge; I didn’t expect the level of quality and depth they were able to provide in an online lecture format,” he says. “Having access to this kind of content — it’s a privilege, and now that we have it, we have to make the most of it.”

      A refreshing investment

      As an applied mathematician with 15 years of experience in the U.S. defense sector, Celia Wilson says she felt comfortable with her knowledge, though not 100 percent confident that her math skills could stand up against the next generation.

      “I felt I was getting left behind,” she says. “So I decided to take some time out and invest in myself, and this program was a great opportunity to systematize and refresh my knowledge of statistics and data science.”

      Since completing the course, Wilson says she has secured a new job as a director of data and analytics, where she is confident in her ability to manage a team of the “new breed of data scientists.” It turns out, however, that completing the program has given her an even greater gift than self-confidence.

      “Most importantly,” she adds, “it’s inspired my daughters to tell anyone who will listen that math is definitely for girls.”

      Connecting an engaged community

      Each course is connected to an online forum that allows learners to enhance their experience through real-time conversations with others in their cohort.

      “We have worked hard to provide a scalable version of the traditional teaching assistant support system that you would get in a usual on-campus class, with a great online forum for people to connect with each other as learners,” Shah says.

      David Khachatrian, a data scientist working on improving the drug discovery pipeline, says that leveraging the community to hone his ability to “think clearly and communicate effectively with others” mattered more than anything.

      “Take the opportunity to engage with your community of fellow learners and facilitators — answer questions for others to give back to the community, solidify your own understanding, and practice your ability to explain clearly,” Khachatrian says. “These skills and behaviors will help you to succeed not just in SDS, but wherever you go in the future.”

      “There were a lot of active contributions from a lot of learners and I felt it was really a very strong component of the course,” da Silva Branco Magalhaes adds. “I had some offline contact with other students who are connections that I’ve kept up with to this day.”

      A solid path forward

      “We have a dedicated team supporting the MM SDS community on the MIT side,” Shah says, citing the contributions of Karene Chu, MM SDS assistant director of education; Susana Kevorkova, the MM SDS program manager; and Jeremy Rossen, MM program coordinator. “They’ve done so much to ensure the success of the program and our learners, and they are constantly adding value to the program — like identifying real-time supplementary opportunities for learners to participate in, including the IDSS Policy Hackathon.”

      The program now holds online “graduation” ceremonies, where credential holders from all over the world share their experiences. Says Shah, who looks forward to celebrating the next 1,000 learners: “Every time I think about it, I feel emotional. It feels great, and it keeps us going.” More

    • 75 Shares119 Views

      in Data Management & Statistics

      Efficient technique improves machine-learning models’ reliability

      by

      Powerful machine-learning models are being used to help people tackle tough problems such as identifying disease in medical images or detecting road obstacles for autonomous vehicles. But machine-learning models can make mistakes, so in high-stakes settings it’s critical that humans know when to trust a model’s predictions.

      Uncertainty quantification is one tool that improves a model’s reliability; the model produces a score along with the prediction that expresses a confidence level that the prediction is correct. While uncertainty quantification can be useful, existing methods typically require retraining the entire model to give it that ability. Training involves showing a model millions of examples so it can learn a task. Retraining then requires millions of new data inputs, which can be expensive and difficult to obtain, and also uses huge amounts of computing resources.

      Researchers at MIT and the MIT-IBM Watson AI Lab have now developed a technique that enables a model to perform more effective uncertainty quantification, while using far fewer computing resources than other methods, and no additional data. Their technique, which does not require a user to retrain or modify a model, is flexible enough for many applications.

      The technique involves creating a simpler companion model that assists the original machine-learning model in estimating uncertainty. This smaller model is designed to identify different types of uncertainty, which can help researchers drill down on the root cause of inaccurate predictions.

      “Uncertainty quantification is essential for both developers and users of machine-learning models. Developers can utilize uncertainty measurements to help develop more robust models, while for users, it can add another layer of trust and reliability when deploying models in the real world. Our work leads to a more flexible and practical solution for uncertainty quantification,” says Maohao Shen, an electrical engineering and computer science graduate student and lead author of a paper on this technique.

      Shen wrote the paper with Yuheng Bu, a former postdoc in the Research Laboratory of Electronics (RLE) who is now an assistant professor at the University of Florida; Prasanna Sattigeri, Soumya Ghosh, and Subhro Das, research staff members at the MIT-IBM Watson AI Lab; and senior author Gregory Wornell, the Sumitomo Professor in Engineering who leads the Signals, Information, and Algorithms Laboratory RLE and is a member of the MIT-IBM Watson AI Lab. The research will be presented at the AAAI Conference on Artificial Intelligence.

      Quantifying uncertainty

      In uncertainty quantification, a machine-learning model generates a numerical score with each output to reflect its confidence in that prediction’s accuracy. Incorporating uncertainty quantification by building a new model from scratch or retraining an existing model typically requires a large amount of data and expensive computation, which is often impractical. What’s more, existing methods sometimes have the unintended consequence of degrading the quality of the model’s predictions.

      The MIT and MIT-IBM Watson AI Lab researchers have thus zeroed in on the following problem: Given a pretrained model, how can they enable it to perform effective uncertainty quantification?

      They solve this by creating a smaller and simpler model, known as a metamodel, that attaches to the larger, pretrained model and uses the features that larger model has already learned to help it make uncertainty quantification assessments.

      “The metamodel can be applied to any pretrained model. It is better to have access to the internals of the model, because we can get much more information about the base model, but it will also work if you just have a final output. It can still predict a confidence score,” Sattigeri says.

      They design the metamodel to produce the uncertainty quantification output using a technique that includes both types of uncertainty: data uncertainty and model uncertainty. Data uncertainty is caused by corrupted data or inaccurate labels and can only be reduced by fixing the dataset or gathering new data. In model uncertainty, the model is not sure how to explain the newly observed data and might make incorrect predictions, most likely because it hasn’t seen enough similar training examples. This issue is an especially challenging but common problem when models are deployed. In real-world settings, they often encounter data that are different from the training dataset.

      “Has the reliability of your decisions changed when you use the model in a new setting? You want some way to have confidence in whether it is working in this new regime or whether you need to collect training data for this particular new setting,” Wornell says.

      Validating the quantification

      Once a model produces an uncertainty quantification score, the user still needs some assurance that the score itself is accurate. Researchers often validate accuracy by creating a smaller dataset, held out from the original training data, and then testing the model on the held-out data. However, this technique does not work well in measuring uncertainty quantification because the model can achieve good prediction accuracy while still being over-confident, Shen says.

      They created a new validation technique by adding noise to the data in the validation set — this noisy data is more like out-of-distribution data that can cause model uncertainty. The researchers use this noisy dataset to evaluate uncertainty quantifications.

      They tested their approach by seeing how well a meta-model could capture different types of uncertainty for various downstream tasks, including out-of-distribution detection and misclassification detection. Their method not only outperformed all the baselines in each downstream task but also required less training time to achieve those results.

      This technique could help researchers enable more machine-learning models to effectively perform uncertainty quantification, ultimately aiding users in making better decisions about when to trust predictions.

      Moving forward, the researchers want to adapt their technique for newer classes of models, such as large language models that have a different structure than a traditional neural network, Shen says.

      The work was funded, in part, by the MIT-IBM Watson AI Lab and the U.S. National Science Foundation. More

    • 88 Shares149 Views

      in Data Management & Statistics

      Helping companies deploy AI models more responsibly

      by

      Companies today are incorporating artificial intelligence into every corner of their business. The trend is expected to continue until machine-learning models are incorporated into most of the products and services we interact with every day.

      As those models become a bigger part of our lives, ensuring their integrity becomes more important. That’s the mission of Verta, a startup that spun out of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL).

      Verta’s platform helps companies deploy, monitor, and manage machine-learning models safely and at scale. Data scientists and engineers can use Verta’s tools to track different versions of models, audit them for bias, test them before deployment, and monitor their performance in the real world.

      “Everything we do is to enable more products to be built with AI, and to do that safely,” Verta founder and CEO Manasi Vartak SM ’14, PhD ’18 says. “We’re already seeing with ChatGPT how AI can be used to generate data, artefacts — you name it — that look correct but aren’t correct. There needs to be more governance and control in how AI is being used, particularly for enterprises providing AI solutions.”

      Verta is currently working with large companies in health care, finance, and insurance to help them understand and audit their models’ recommendations and predictions. It’s also working with a number of high-growth tech companies looking to speed up deployment of new, AI-enabled solutions while ensuring those solutions are used appropriately.

      Vartak says the company has been able to decrease the time it takes customers to deploy AI models by orders of magnitude while ensuring those models are explainable and fair — an especially important factor for companies in highly regulated industries.

      Health care companies, for example, can use Verta to improve AI-powered patient monitoring and treatment recommendations. Such systems need to be thoroughly vetted for errors and biases before they’re used on patients.

      “Whether it’s bias or fairness or explainability, it goes back to our philosophy on model governance and management,” Vartak says. “We think of it like a preflight checklist: Before an airplane takes off, there’s a set of checks you need to do before you get your airplane off the ground. It’s similar with AI models. You need to make sure you’ve done your bias checks, you need to make sure there’s some level of explainability, you need to make sure your model is reproducible. We help with all of that.”

      From project to product

      Before coming to MIT, Vartak worked as a data scientist for a social media company. In one project, after spending weeks tuning machine-learning models that curated content to show in people’s feeds, she learned an ex-employee had already done the same thing. Unfortunately, there was no record of what they did or how it affected the models.

      For her PhD at MIT, Vartak decided to build tools to help data scientists develop, test, and iterate on machine-learning models. Working in CSAIL’s Database Group, Vartak recruited a team of graduate students and participants in MIT’s Undergraduate Research Opportunities Program (UROP).

      “Verta would not exist without my work at MIT and MIT’s ecosystem,” Vartak says. “MIT brings together people on the cutting edge of tech and helps us build the next generation of tools.”

      The team worked with data scientists in the CSAIL Alliances program to decide what features to build and iterated based on feedback from those early adopters. Vartak says the resulting project, named ModelDB, was the first open-source model management system.

      Vartak also took several business classes at the MIT Sloan School of Management during her PhD and worked with classmates on startups that recommended clothing and tracked health, spending countless hours in the Martin Trust Center for MIT Entrepreneurship and participating in the center’s delta v summer accelerator.

      “What MIT lets you do is take risks and fail in a safe environment,” Vartak says. “MIT afforded me those forays into entrepreneurship and showed me how to go about building products and finding first customers, so by the time Verta came around I had done it on a smaller scale.”

      ModelDB helped data scientists train and track models, but Vartak quickly saw the stakes were higher once models were deployed at scale. At that point, trying to improve (or accidentally breaking) models can have major implications for companies and society. That insight led Vartak to begin building Verta.

      “At Verta, we help manage models, help run models, and make sure they’re working as expected, which we call model monitoring,” Vartak explains. “All of those pieces have their roots back to MIT and my thesis work. Verta really evolved from my PhD project at MIT.”

      Verta’s platform helps companies deploy models more quickly, ensure they continue working as intended over time, and manage the models for compliance and governance. Data scientists can use Verta to track different versions of models and understand how they were built, answering questions like how data were used and which explainability or bias checks were run. They can also vet them by running them through deployment checklists and security scans.

      “Verta’s platform takes the data science model and adds half a dozen layers to it to transform it into something you can use to power, say, an entire recommendation system on your website,” Vartak says. “That includes performance optimizations, scaling, and cycle time, which is how quickly you can take a model and turn it into a valuable product, as well as governance.”

      Supporting the AI wave

      Vartak says large companies often use thousands of different models that influence nearly every part of their operations.

      “An insurance company, for example, will use models for everything from underwriting to claims, back-office processing, marketing, and sales,” Vartak says. “So, the diversity of models is really high, there’s a large volume of them, and the level of scrutiny and compliance companies need around these models are very high. They need to know things like: Did you use the data you were supposed to use? Who were the people who vetted it? Did you run explainability checks? Did you run bias checks?”

      Vartak says companies that don’t adopt AI will be left behind. The companies that ride AI to success, meanwhile, will need well-defined processes in place to manage their ever-growing list of models.

      “In the next 10 years, every device we interact with is going to have intelligence built in, whether it’s a toaster or your email programs, and it’s going to make your life much, much easier,” Vartak says. “What’s going to enable that intelligence are better models and software, like Verta, that help you integrate AI into all of these applications very quickly.” More

    • 113 Shares149 Views

      in Data Management & Statistics

      3 Questions: Leo Anthony Celi on ChatGPT and medicine

      by

      Launched in November 2022, ChatGPT is a chatbot that can not only engage in human-like conversation, but also provide accurate answers to questions in a wide range of knowledge domains. The chatbot, created by the firm OpenAI, is based on a family of “large language models” — algorithms that can recognize, predict, and generate text based on patterns they identify in datasets containing hundreds of millions of words.

      In a study appearing in PLOS Digital Health this week, researchers report that ChatGPT performed at or near the passing threshold of the U.S. Medical Licensing Exam (USMLE) — a comprehensive, three-part exam that doctors must pass before practicing medicine in the United States. In an editorial accompanying the paper, Leo Anthony Celi, a principal research scientist at MIT’s Institute for Medical Engineering and Science, a practicing physician at Beth Israel Deaconess Medical Center, and an associate professor at Harvard Medical School, and his co-authors argue that ChatGPT’s success on this exam should be a wake-up call for the medical community.

      Q: What do you think the success of ChatGPT on the USMLE reveals about the nature of the medical education and evaluation of students? 

      A: The framing of medical knowledge as something that can be encapsulated into multiple choice questions creates a cognitive framing of false certainty. Medical knowledge is often taught as fixed model representations of health and disease. Treatment effects are presented as stable over time despite constantly changing practice patterns. Mechanistic models are passed on from teachers to students with little emphasis on how robustly those models were derived, the uncertainties that persist around them, and how they must be recalibrated to reflect advances worthy of incorporation into practice. 

      ChatGPT passed an examination that rewards memorizing the components of a system rather than analyzing how it works, how it fails, how it was created, how it is maintained. Its success demonstrates some of the shortcomings in how we train and evaluate medical students. Critical thinking requires appreciation that ground truths in medicine continually shift, and more importantly, an understanding how and why they shift.

      Q: What steps do you think the medical community should take to modify how students are taught and evaluated?  

      A: Learning is about leveraging the current body of knowledge, understanding its gaps, and seeking to fill those gaps. It requires being comfortable with and being able to probe the uncertainties. We fail as teachers by not teaching students how to understand the gaps in the current body of knowledge. We fail them when we preach certainty over curiosity, and hubris over humility.  

      Medical education also requires being aware of the biases in the way medical knowledge is created and validated. These biases are best addressed by optimizing the cognitive diversity within the community. More than ever, there is a need to inspire cross-disciplinary collaborative learning and problem-solving. Medical students need data science skills that will allow every clinician to contribute to, continually assess, and recalibrate medical knowledge.

      Q: Do you see any upside to ChatGPT’s success in this exam? Are there beneficial ways that ChatGPT and other forms of AI can contribute to the practice of medicine? 

      A: There is no question that large language models (LLMs) such as ChatGPT are very powerful tools in sifting through content beyond the capabilities of experts, or even groups of experts, and extracting knowledge. However, we will need to address the problem of data bias before we can leverage LLMs and other artificial intelligence technologies. The body of knowledge that LLMs train on, both medical and beyond, is dominated by content and research from well-funded institutions in high-income countries. It is not representative of most of the world.

      We have also learned that even mechanistic models of health and disease may be biased. These inputs are fed to encoders and transformers that are oblivious to these biases. Ground truths in medicine are continuously shifting, and currently, there is no way to determine when ground truths have drifted. LLMs do not evaluate the quality and the bias of the content they are being trained on. Neither do they provide the level of uncertainty around their output. But the perfect should not be the enemy of the good. There is tremendous opportunity to improve the way health care providers currently make clinical decisions, which we know are tainted with unconscious bias. I have no doubt AI will deliver its promise once we have optimized the data input. More

    • 100 Shares159 Views

      in Data Management & Statistics

      When should data scientists try a new technique?

      by

      If a scientist wanted to forecast ocean currents to understand how pollution travels after an oil spill, she could use a common approach that looks at currents traveling between 10 and 200 kilometers. Or, she could choose a newer model that also includes shorter currents. This might be more accurate, but it could also require learning new software or running new computational experiments. How to know if it will be worth the time, cost, and effort to use the new method?

      A new approach developed by MIT researchers could help data scientists answer this question, whether they are looking at statistics on ocean currents, violent crime, children’s reading ability, or any number of other types of datasets.

      The team created a new measure, known as the “c-value,” that helps users choose between techniques based on the chance that a new method is more accurate for a specific dataset. This measure answers the question “is it likely that the new method is more accurate for this data than the common approach?”

      Traditionally, statisticians compare methods by averaging a method’s accuracy across all possible datasets. But just because a new method is better for all datasets on average doesn’t mean it will actually provide a better estimate using one particular dataset. Averages are not application-specific.

      So, researchers from MIT and elsewhere created the c-value, which is a dataset-specific tool. A high c-value means it is unlikely a new method will be less accurate than the original method on a specific data problem.

      In their proof-of-concept paper, the researchers describe and evaluate the c-value using real-world data analysis problems: modeling ocean currents, estimating violent crime in neighborhoods, and approximating student reading ability at schools. They show how the c-value could help statisticians and data analysts achieve more accurate results by indicating when to use alternative estimation methods they otherwise might have ignored.

      “What we are trying to do with this particular work is come up with something that is data specific. The classical notion of risk is really natural for someone developing a new method. That person wants their method to work well for all of their users on average. But a user of a method wants something that will work on their individual problem. We’ve shown that the c-value is a very practical proof-of-concept in that direction,” says senior author Tamara Broderick, an associate professor in the Department of Electrical Engineering and Computer Science (EECS) and a member of the Laboratory for Information and Decision Systems and the Institute for Data, Systems, and Society.

      She’s joined on the paper by Brian Trippe PhD ’22, a former graduate student in Broderick’s group who is now a postdoc at Columbia University; and Sameer Deshpande ’13, a former postdoc in Broderick’s group who is now an assistant professor at the University of Wisconsin at Madison. An accepted version of the paper is posted online in the Journal of the American Statistical Association.

      Evaluating estimators

      The c-value is designed to help with data problems in which researchers seek to estimate an unknown parameter using a dataset, such as estimating average student reading ability from a dataset of assessment results and student survey responses. A researcher has two estimation methods and must decide which to use for this particular problem.

      The better estimation method is the one that results in less “loss,” which means the estimate will be closer to the ground truth. Consider again the forecasting of ocean currents: Perhaps being off by a few meters per hour isn’t so bad, but being off by many kilometers per hour makes the estimate useless. The ground truth is unknown, though; the scientist is trying to estimate it. Therefore, one can never actually compute the loss of an estimate for their specific data. That’s what makes comparing estimates challenging. The c-value helps a scientist navigate this challenge.

      The c-value equation uses a specific dataset to compute the estimate with each method, and then once more to compute the c-value between the methods. If the c-value is large, it is unlikely that the alternative method is going to be worse and yield less accurate estimates than the original method.

      “In our case, we are assuming that you conservatively want to stay with the default estimator, and you only want to go to the new estimator if you feel very confident about it. With a high c-value, it’s likely that the new estimate is more accurate. If you get a low c-value, you can’t say anything conclusive. You might have actually done better, but you just don’t know,” Broderick explains.

      Probing the theory

      The researchers put that theory to the test by evaluating three real-world data analysis problems.

      For one, they used the c-value to help determine which approach is best for modeling ocean currents, a problem Trippe has been tackling. Accurate models are important for predicting the dispersion of contaminants, like pollution from an oil spill. The team found that estimating ocean currents using multiple scales, one larger and one smaller, likely yields higher accuracy than using only larger scale measurements.

      “Oceans researchers are studying this, and the c-value can provide some statistical ‘oomph’ to support modeling the smaller scale,” Broderick says.

      In another example, the researchers sought to predict violent crime in census tracts in Philadelphia, an application Deshpande has been studying. Using the c-value, they found that one could get better estimates about violent crime rates by incorporating information about census-tract-level nonviolent crime into the analysis. They also used the c-value to show that additionally leveraging violent crime data from neighboring census tracts in the analysis isn’t likely to provide further accuracy improvements.

      “That doesn’t mean there isn’t an improvement, that just means that we don’t feel confident saying that you will get it,” she says.

      Now that they have proven the c-value in theory and shown how it could be used to tackle real-world data problems, the researchers want to expand the measure to more types of data and a wider set of model classes.

      The ultimate goal is to create a measure that is general enough for many more data analysis problems, and while there is still a lot of work to do to realize that objective, Broderick says this is an important and exciting first step in the right direction.

      This research was supported, in part, by an Advanced Research Projects Agency-Energy grant, a National Science Foundation CAREER Award, the Office of Naval Research, and the Wisconsin Alumni Research Foundation. More

    • 63 Shares129 Views

      in Data Management & Statistics

      Putting clear bounds on uncertainty

      by

      In science and technology, there has been a long and steady drive toward improving the accuracy of measurements of all kinds, along with parallel efforts to enhance the resolution of images. An accompanying goal is to reduce the uncertainty in the estimates that can be made, and the inferences drawn, from the data (visual or otherwise) that have been collected. Yet uncertainty can never be wholly eliminated. And since we have to live with it, at least to some extent, there is much to be gained by quantifying the uncertainty as precisely as possible.

      Expressed in other terms, we’d like to know just how uncertain our uncertainty is.

      That issue was taken up in a new study, led by Swami Sankaranarayanan, a postdoc at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), and his co-authors — Anastasios Angelopoulos and Stephen Bates of the University of California at Berkeley; Yaniv Romano of Technion, the Israel Institute of Technology; and Phillip Isola, an associate professor of electrical engineering and computer science at MIT. These researchers succeeded not only in obtaining accurate measures of uncertainty, they also found a way to display uncertainty in a manner the average person could grasp.

      Their paper, which was presented in December at the Neural Information Processing Systems Conference in New Orleans, relates to computer vision — a field of artificial intelligence that involves training computers to glean information from digital images. The focus of this research is on images that are partially smudged or corrupted (due to missing pixels), as well as on methods — computer algorithms, in particular — that are designed to uncover the part of the signal that is marred or otherwise concealed. An algorithm of this sort, Sankaranarayanan explains, “takes the blurred image as the input and gives you a clean image as the output” — a process that typically occurs in a couple of steps.

      First, there is an encoder, a kind of neural network specifically trained by the researchers for the task of de-blurring fuzzy images. The encoder takes a distorted image and, from that, creates an abstract (or “latent”) representation of a clean image in a form — consisting of a list of numbers — that is intelligible to a computer but would not make sense to most humans. The next step is a decoder, of which there are a couple of types, that are again usually neural networks. Sankaranarayanan and his colleagues worked with a kind of decoder called a “generative” model. In particular, they used an off-the-shelf version called StyleGAN, which takes the numbers from the encoded representation (of a cat, for instance) as its input and then constructs a complete, cleaned-up image (of that particular cat). So the entire process, including the encoding and decoding stages, yields a crisp picture from an originally muddied rendering.

      But how much faith can someone place in the accuracy of the resultant image? And, as addressed in the December 2022 paper, what is the best way to represent the uncertainty in that image? The standard approach is to create a “saliency map,” which ascribes a probability value — somewhere between 0 and 1 — to indicate the confidence the model has in the correctness of every pixel, taken one at a time. This strategy has a drawback, according to Sankaranarayanan, “because the prediction is performed independently for each pixel. But meaningful objects occur within groups of pixels, not within an individual pixel,” he adds, which is why he and his colleagues are proposing an entirely different way of assessing uncertainty.

      Their approach is centered around the “semantic attributes” of an image — groups of pixels that, when taken together, have meaning, making up a human face, for example, or a dog, or some other recognizable thing. The objective, Sankaranarayanan maintains, “is to estimate uncertainty in a way that relates to the groupings of pixels that humans can readily interpret.”

      Whereas the standard method might yield a single image, constituting the “best guess” as to what the true picture should be, the uncertainty in that representation is normally hard to discern. The new paper argues that for use in the real world, uncertainty should be presented in a way that holds meaning for people who are not experts in machine learning. Rather than producing a single image, the authors have devised a procedure for generating a range of images — each of which might be correct. Moreover, they can set precise bounds on the range, or interval, and provide a probabilistic guarantee that the true depiction lies somewhere within that range. A narrower range can be provided if the user is comfortable with, say, 90 percent certitude, and a narrower range still if more risk is acceptable.

      The authors believe their paper puts forth the first algorithm, designed for a generative model, which can establish uncertainty intervals that relate to meaningful (semantically-interpretable) features of an image and come with “a formal statistical guarantee.” While that is an important milestone, Sankaranarayanan considers it merely a step toward “the ultimate goal. So far, we have been able to do this for simple things, like restoring images of human faces or animals, but we want to extend this approach into more critical domains, such as medical imaging, where our ‘statistical guarantee’ could be especially important.”

      Suppose that the film, or radiograph, of a chest X-ray is blurred, he adds, “and you want to reconstruct the image. If you are given a range of images, you want to know that the true image is contained within that range, so you are not missing anything critical” — information that might reveal whether or not a patient has lung cancer or pneumonia. In fact, Sankaranarayanan and his colleagues have already begun working with a radiologist to see if their algorithm for predicting pneumonia could be useful in a clinical setting.

      Their work may also have relevance in the law enforcement field, he says. “The picture from a surveillance camera may be blurry, and you want to enhance that. Models for doing that already exist, but it is not easy to gauge the uncertainty. And you don’t want to make a mistake in a life-or-death situation.” The tools that he and his colleagues are developing could help identify a guilty person and help exonerate an innocent one as well.

      Much of what we do and many of the things happening in the world around us are shrouded in uncertainty, Sankaranarayanan notes. Therefore, gaining a firmer grasp of that uncertainty could help us in countless ways. For one thing, it can tell us more about exactly what it is we do not know.

      Angelopoulos was supported by the National Science Foundation. Bates was supported by the Foundations of Data Science Institute and the Simons Institute. Romano was supported by the Israel Science Foundation and by a Career Advancement Fellowship from Technion. Sankaranarayanan’s and Isola’s research for this project was sponsored by the U.S. Air Force Research Laboratory and the U.S. Air Force Artificial Intelligence Accelerator and was accomplished under Cooperative Agreement Number FA8750-19-2- 1000. MIT SuperCloud and the Lincoln Laboratory Supercomputing Center also provided computing resources that contributed to the results reported in this work. More