Author: Denis Paiste | Materials Research Laboratory<\/p>\n
The promises and challenges of artificial intelligence and machine learning highlighted the Oct. 9 MIT Materials Day Symposium, with presentations on new ways of forming zeolite compounds, faster drug synthesis, advanced optical devices, and more.<\/p>\n
\u201cMachine learning is having an impact in all areas of materials research,\u201d Materials Research Laboratory Director Carl V. Thompson said.<\/p>\n
\u201cWe\u2019re increasingly able to work in tandem with machines to help us decide what materials to make,\u201d said Elsa A. Olivetti<\/a>, the Atlantic Richfield Associate Professor of Energy Studies. Machine learning is also guiding how to make those materials with new insights into synthesis methods, and, in some cases (such as with robotic systems), actually making those materials, she noted.<\/p>\n Keynote speaker Brian Storey, director of accelerated materials design and discovery at Toyota Research Institute, spoke about machine learning to\u00a0advance the switch\u00a0from the internal combustion engine to electric vehicles, and Professor Ju Li, the Battelle Energy Alliance Professor of Nuclear Science and Engineering and professor of materials science and engineering, spoke about\u00a0atomic engineering\u00a0using elastic strain and radiation nudging of atoms.<\/p>\n Porous materials<\/strong><\/p>\n Olivetti and\u00a0Rafael Gomez-Bombarelli<\/a>, the Toyota Assistant Professor in Materials Processing, worked together to apply machine learning to develop a better understanding of porous materials called zeolites, formed from silicon and aluminum oxide, that have a wide range of uses, from cat litter to petroleum refining.<\/p>\n \u201cEssentially, the idea is that the pore has the right size to hold organic molecules,\u201d Gomez-Bombarelli said. While only about 250 zeolites of this class are known to engineers, physicists can calculate hundreds of thousands of possible ways these structures can form. \u201cSome of them can be converted into each other,\u201d he said. \u201cSo, you could mine one zeolite, put it under pressure, or heat it up, and it becomes a different one that could be more valuable for a specific application.\u201d<\/p>\n A traditional method was to interpret these crystalline structures as a combination of building blocks. However, when zeolite transformations were analyzed, more than half the time there were no building blocks in common between the original zeolite before the change and the new zeolite after the change. \u201cBuilding block theory has some interesting ingredients, but doesn\u2019t quite explain the rules to go from A to B,\u201d Gomez-Bombarelli said.<\/p>\n Graph-based approach<\/strong><\/p>\n Gomez-Bombarelli\u2019s new\u00a0graph-based approach\u00a0finds that when each zeolite framework structure is represented as a graph, these graphs match before and after in zeolite transformation pairs. \u201cSome classes of transformations only happen between zeolites that have the same graph,\u201d he said.<\/p>\n This work evolved from Olivetti\u2019s data mining of 2.5 million materials science journal articles to uncover recipes for making different inorganic materials. The zeolite study examined 70,000 papers. \u201cOne of the challenges in learning from the literature is we publish positive examples, we publish data of things that went well,\u201d Olivetti said. In the zeolite community, researchers also publish what doesn\u2019t work. \u201cThat\u2019s a valuable dataset for us to learn from,\u201d she said. \u201cWhat we\u2019ve been able to use this dataset for is to try to predict potential synthesis pathways for making particular types of zeolites.\u201d<\/p>\n In earlier work with colleagues at the University of Massachusetts, Olivetti developed a system that identified common scientific words and techniques found in sentences across this large library and brought together similar findings. \u201cOne important challenge in natural language processing is to draw this linked information across a document,\u201d Olivetti explained. \u201cWe are trying to build tools that are able to do that linking,\u201d Olivetti says.<\/p>\n AI-assisted chemical synthesis<\/strong><\/p>\n Klavs F. Jensen<\/a>, the Warren K. Lewis Professor of Chemical Engineering and Professor of Materials Science and Engineering, described a\u00a0chemical synthesis system<\/a>\u00a0that combines artificial intelligence-guided processing steps with a robotically operated modular reaction system.<\/p>\n For those unfamiliar with synthesis, Jensen explained that \u201cYou have reactants you start with, you have reagents that you have to add, catalysts and so forth to make the reaction go, you have intermediates, and ultimately you end up with your product.\u201d<\/p>\n The artificial intelligence system combed 12.5 million reactions, creating a set of rules, or library, from about 160,000 of the most commonly used synthesis recipes, Jensen relates. This machine learning approach suggests processing conditions such as what catalysts, solvents, and reagents to use in the reaction.<\/p>\n \u201cYou can have the system take whatever information it got from the published literature about conditions and so on and you can use that to form a recipe,\u201d he says. Because there is not enough data yet to inform the system, a chemical expert still needs to step in to specify concentrations, flow rates, and process stack configurations, and to ensure safety before sending the recipe to the robotic system.<\/p>\n The researchers\u00a0demonstrated this system<\/a>\u00a0by predicting synthesis plans for 15 drugs or drug-like molecules \u2014 the painkiller lidocaine, for example, and several high blood pressure drugs \u2014 and then making them with the system. The flow reactor system contrasts with a batch system. \u201cIn order to be able to accelerate the reactions, we use typically much more aggressive conditions than are done in batch \u2014 high temperatures and higher pressures,\u201d Jensen says.<\/p>\n The modular system consists of a processing tower with interchangeable reaction modules and a set of different reagents, which are connected together by the robot for each synthesis. These findings were reported in\u00a0Science<\/em><\/a>.<\/p>\n Former PhD students Connor W. Coley and Dale A. Thomas built the computer-aided synthesis planner and the flow reactor system, respectively, and former postdoc Justin A. M. Lummiss did the chemistry along with a large team of MIT Undergraduate Research Opportunity Program students, PhD students, and postdocs. Jensen also notes contributions from MIT faculty colleagues Regina Barzilay, William H. Green, A. John Hart, Tommi Jaakkola, and Tim Jamison. MIT has filed a patent for the robotic handling of fluid connections. The software suite that suggests and prioritizes possible synthesis routes is open source, and an online version is at the ASKCOS website<\/a>.<\/p>\n Robustness in machine learning<\/strong><\/p>\n Deep learning systems perform amazingly well on benchmark tasks such as images and natural language processing applications, said Professor\u00a0Asu Ozdaglar<\/a>, who heads MIT\u2019s Department of Electrical Engineering and Computer Science. Still, researchers are far from understanding why these deep learning systems work, when they will work, and how they generalize. And when they get things wrong, they can go completely awry.<\/p>\n Ozdaglar gave an example of an image with a state-of-the-art classifier that can look at a picture of a cute pig and recognize the image as that of a pig. But, \u201cIf you add a little bit of, very little, perturbation, what happens is basically the same classifier thinks that\u2019s an airliner,\u201d Ozdaglar said. \u201cSo this is sort of an example where people say machine learning is so powerful, it can make pigs fly,\u201d she said, accompanied by audience laughter. \u201cAnd this immediately tells us basically we have to go beyond our standard approaches.\u201d<\/p>\n A potential solution lies in an optimization formulation known as a Minimax, or MinMax, problem. Another place where MinMax formulation arises is in generative adversarial network, or GAN, training. Using an example of images of real cars and fake images of cars, Ozdaglar explained, \u201cWe would like these fake images to be drawn from the same distribution as the training set, and this is achieved using two neural networks competing with each other, a generator network and a discriminator network. The generator network creates from random noise these fake images that the discriminator network tries to pull apart to see whether this is real or fake.\u201d<\/p>\n \u201cIt\u2019s basically another MinMax problem whereby the generator is trying to minimize the distance between these two distributions, fake and real. And then the discriminator is trying to maximize that,\u201d she said. The MinMax problem approach has become the backbone of robust training of deep learning systems, she noted.<\/p>\n Ozdaglar added that EECS faculty are applying machine learning to new areas, including health care, citing the work of\u00a0Regina Barzilay<\/a>\u00a0in detecting breast cancer and\u00a0David Sontag<\/a>\u00a0in using electronic medical records for medical diagnosis and treatment.<\/p>\n The EECS undergraduate machine learning course (6.036) hosted 800 students last spring, and consistently has 600 or more students enrolled, making it the most popular course at MIT. The new Stephen A. Schwarzman College of Computing provides an opportunity to create a more dynamic and adaptable structure than MIT\u2019s traditional department structure. For example, one idea is to create several cross-departmental teaching groups. \u201cWe envision things like courses in the foundations of computing, computational science and engineering, social studies of computing, and have these courses taken by all of our students taught jointly by our faculty across MIT,\u201d she said.<\/p>\n Optical advantage<\/strong><\/p>\n Juejun “JJ” Hu<\/a>, associate professor of materials science and engineering, detailed his research coupling a silicon chip-based spectrometer for detecting infrared light wavelengths to a newly created machine learning algorithm. Ordinary spectrometers, going back to Isaac Newton\u2019s first prism, work by splitting light, which reduces intensity, but Hu\u2019s version collects all of the light at a single detector, which preserves light intensity but then poses the problem of identifying different wavelengths from a single capture.<\/p>\n \u201cIf you want to solve this trade-off between the (spectral) resolution and the signal-to-noise ratio, what you have to do is resort to a new type of spectroscopy tool called wavelength multiplexing spectrometer,\u201d Hu said. His new\u00a0spectrometer architecture<\/a>, which is called digital Fourier transform spectroscopy, incorporates tunable optical switches on a silicon chip. The device works by measuring the intensity of light at different optical switch settings and comparing the results. \u201cWhat you have is essentially a group of linear equations that gives you some linear combination of the light intensity at different wavelengths in the form of a detector reading,\u201d he said.<\/p>\n A prototype device with six switches supports a total of 64 unique optical states, which can provide 64 independent readings. \u201cThe advantage of this new device architecture is that the performance doubles every time you add a new switch,\u201d he said. Working with\u00a0Brando Miranda<\/a>\u00a0at the Center for Brains Minds and Machines at MIT, he developed a new algorithm,\u00a0Elastic D1<\/a>, that gives a resolution down to 0.2 nanometers and gives an accurate light measurement with only two consecutive measurements.<\/p>\n \u201cWe believe this kind of unique combination between the hardware of a new spectrometer architecture and the algorithm can enable a wide range of applications ranging from industrial process monitoring to medical imaging,\u201d Hu said. Hu also is applying machine learning in his work on complex optical media such as metasurfaces, which are new optical devices featuring an array of specially designed optical antennas that add a phase delay to the incoming light.<\/p>\n Poster session winners<\/strong><\/p>\n Nineteen MIT postdocs and graduate students gave two-minute talks about their research during a poster session preview. At the Materials Day\u00a0Poster Session\u00a0immediately following the symposium, award winners were mechanical engineering graduate student Erin Looney, media arts and sciences graduate student Bianca Datta, and materials science and engineering postdoc Michael Chon.<\/p>\n The Materials Research Laboratory<\/a> serves interdisciplinary groups of faculty, staff, and students, supported by industry, foundations, and government agencies to carry out fundamental engineering research on materials. Research topics include energy conversion and storage, quantum materials, spintronics, photonics, metals, integrated microsystems, materials sustainability, solid-state ionics, complex oxide electronic properties, biogels, and functional fibers.<\/p>\n<\/div>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Author: Denis Paiste | Materials Research Laboratory The promises and challenges of artificial intelligence and machine learning highlighted the Oct. 9 MIT Materials Day Symposium, […] Read More<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":468,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"footnotes":""},"categories":[24],"tags":[],"_links":{"self":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/2781"}],"collection":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/comments?post=2781"}],"version-history":[{"count":0,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/2781\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media\/463"}],"wp:attachment":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media?parent=2781"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/categories?post=2781"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/tags?post=2781"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}