wins Google grant to boost network communication<img alt="" src="/Profiles/PublishingImages/Guerin_Guerin.jpg?RenditionID=1" style="BORDER:0px solid;" /><p>​Roch Guérin, chair of computer science and engineering at the McKelvey School of Engineering and the Harold B. & Adelaide G. Welge Professor of Computer Science, received a $48,506 grant from Google to study networks that connect data centers.</p>The grant will fund research aimed at making communication in these networks more efficient, getting information where it needs to go in time while also using less bandwidth during peak times, thereby lowering costs.<br/>Roch GuérinThe Source<p> $48,506 grant will go toward studying networks that connect data centers<br/></p> scientific discovery through intelligent experimental design <img alt="" src="/Profiles/PublishingImages/Garnett_Roman.jpg?RenditionID=1" style="BORDER:0px solid;" /><div id="__publishingReusableFragmentIdSection"><a href="/ReusableContent/36_.000">a</a></div><p>Within two decades, tools from machine learning will likely be a standard tool in engineering and scientific discovery. Scientists are building better and better instruments to collect more and more data. But someone — or something — must analyze that data to extract scientific knowledge.</p><p>Roman Garnett, in the McKelvey School of Engineering at Washington University in St. Louis, will build new algorithms for a method known as active machine learning that will accelerate extracting knowledge from big data with a five-year, $497,693 CAREER Award from the National Science Foundation (NSF). The awards support junior faculty who model the role of teacher-scholar through outstanding research, excellent education and the integration of education and research within the context of the mission of their organization. One-third of current McKelvey Engineering faculty have received the award.</p><p>In some situations, analyzing new data requires expensive processes such as running a simulation on a supercomputer or having a human perform the analysis in a lab. With active machine learning, scientists can automatically and adaptively design experiments to make the best use of limited resources. Active machine learning can be considered an automated approach to the scientific method.</p><p>"We take data that we've already collected and use it to give us an idea about what is happening," said Garnett, assistant professor of computer science & engineering. "Then we build a model to reason about what outcomes of new experiments might be based on what we've already learned. We use that model with our goals to develop a rule or method to look at a large collection of data and identify what is the most useful. The hope is that we are able to achieve our goal more efficiently than we would have with, for example, randomly-selected data."</p><p>For instance, Garnett said astronomers are building better telescopes to get a better look at stars, galaxies <g class="gr_ gr_53 gr-alert gr_gramm gr_inline_cards gr_run_anim Punctuation only-ins replaceWithoutSep" id="53" data-gr-id="53">and</g> quasars in the sky. Thousands of these objects can be imaged in one night, creating hundreds of gigabytes of data. That's where Garnett's work comes in.</p><p>"Having the data is not the point," he said. "You want to extract some knowledge. Now we've got a thousand times more data than we used to have, so we have an even bigger challenge. Astronomers are now resorting to 'citizen-scientist' volunteers to analyze some of these images to classify the objects and search for rare phenomena. There is a big challenge in effectively prioritizing the data for these volunteers to make the best use of their time."</p><p>Garnett's research will develop automated tools to quickly extract scientific knowledge in situations such as these.</p><p>Garnett and his team also will continue to develop the field of active search, which he founded, into a new tool to automatically find new members of a valuable class within a dataset, such as finding new materials for drug discovery.  <br/></p><blockquote>"It's a blessing and a curse because you know that whatever you're looking for is going to be in the data somewhere, but now you have to find it," he said.</blockquote><p>"For example, you might take an image of a thousand lights in the sky, but maybe you're searching for one special kind of object. It could be that you don't care about 99 percent of the data because you're searching for examples of this rare phenomenon. Now your goal is to try to find a needle in the haystack."</p><p>In addition, Garnett's team will increase access to active machine learning by building fully automated procedures. His lab will further the field of automated machine learning (AutoML), which uses machine learning to automate the process of machine learning itself, Garnett said. This will be particularly useful for scientists and engineers who want to adopt active machine learning to help analyze their data.</p><p>"AutoML /helps them adaptively improve the models that we're using for the experimental design. We can automatically build useful models just from their data, opening the power of these techniques to a wide audience" he said.</p><p>As part of his research, Garnett will develop an undergraduate course on sequential decision making as well as work with other faculty members to incorporate active machine learning into other engineering and science courses. He also plans to work with citizen-scientists who are working with astronomers to find new galaxies through a collaboration with Zooniverse. In addition, he is co-writing a book on Bayesian optimization.<br/></p><SPAN ID="__publishingReusableFragment"></SPAN><p><br/></p><span> <div class="cstm-section"><div><h3 style="margin-top: 0px; font-family: "open sans", sans-serif; font-size: 1.34em; text-align: center; border-bottom-width: 1px; border-bottom-style: solid; border-bottom-color: #b0b0b0; padding-bottom: 12px;">Roman Garnett<br/></h3><div style="color: #343434;"><div style="text-align: center;"> </div><ul style="padding-left: 20px;"><li>Assistant Professor of Computer Science & Engineering <br/></li><li>Expertise: Bayesian machine-learning techniques for sequential decision making<br/></li></ul><p style="text-align: center;"> <a href="/Profiles/Pages/Roman-Garnett.aspx" style="background-color: #ffffff;">View Bio</a> <br/></p></div></div></div></span><br/>Garnett's research will develop automated tools to quickly extract scientific knowledge from big data. Beth Miller 2019-04-18T05:00:00ZRoman Garnett will build new algorithms for active machine learning that will accelerate extracting knowledge from big data with an NSF CAREER Award. <p>​Garnett earns NSF CAREER Award<br/></p> take first place at Deloitte coding competition<img alt="Ryan Xu, Patrick Naughton, Pranav Maddula and Yiheng Yao pose with their prize following the competition." src="/news/PublishingImages/deloitte-coding-competition.jpg?RenditionID=1" style="BORDER:0px solid;" />A team of students from the McKelvey School of Engineering took first place at the 2019 Deloitte Capture the Flag Competition.<div><br/></div><div>Students Pranav Maddula, Patrick Naughton,  Ryan Xu, and Yiheng Yao won $3,000 at the competition, hosted by Venture Café St. Louis. Maddula Naughton and Xu are sophomores, and Yao is a first-year student.</div><div><br/></div><div>“I was really happy and surprised we won,” said Xu, who is majoring in computer engineering. “This was the first time I've participated in this kind of competition, so I went in without any experience or expectations. We definitely are looking to participate in more competitions like this.”</div><div><br/></div><div>“I was surprised and happy that we won,” said Naughton, who is pursuing degrees in both computer science and electrical engineering. “It was a real shocker since I had never done this before.”</div><div><br/></div><div>The competition, which challenged students to solve practical cyberchallenges in a simulated environment, assigned students to find a “flag,” or hidden strings of text, and submit them for points.<br/></div>Yiheng Yao, Patrick Naughton, Ryan Xu and Pranav Maddula with their prize after placing first at the competition.Danielle Lacey2019-04-18T05:00:00ZA team of undergraduate students won first place and $3,000 at the 2019 Deloitte Capture the Flag Competition. to develop new method for type of cancer imaging<img alt="" src="/Profiles/PublishingImages/Zang_Weixiong.jpg?RenditionID=2" style="BORDER:0px solid;" /><p>Weixiong Zhang, professor of computer science & engineering in the McKelvey School of Engineering and of genetics at the School of Medicine, has received a two-year, $174,003 grant from the Varian Research Collaboration Program. With the funding, Zhang will develop a new method for semantic image segmentation, a type of computer vision often used to diagnose, plan treatment and provide a prognosis to patients with cancer. The new method will incorporate a spectral graph convolution neural network-based method and a representation scheme of Markov random fields to increase the segmentation accuracy. He is collaborating with Baozhou Sun, assistant professor of radiation oncology at the School of Medicine. They also plan to develop a software system and module that can be integrated into Varian's treatment planning system.<br/></p>Zhang2019-04-11T05:00:00ZWeixiong Zhang will deveop a new type of computer vision often used to diagnose and plan treatment for patients with cancer. McKelvey Engineering faculty working on prestigious MURI collaborations <img alt="Lew, Thimsen, Vorobeychik" src="/news/PublishingImages/three_fac2.jpg?RenditionID=1" style="BORDER:0px solid;" /><div id="__publishingReusableFragmentIdSection"><a href="/ReusableContent/36_.000">a</a></div><p>Three faculty in the McKelvey School of Engineering at Washington University in St. Louis are participating in the U.S. Department of Defense's highly competitive Multidisciplinary University Research Initiative Program (MURI) on projects that may benefit the U.S. military.</p><p>Matthew Lew, assistant professor of electrical & systems engineering; Elijah Thimsen, assistant professor of energy, environmental & chemical engineering; and Yevgeniy Vorobeychik, associate professor of computer science & engineering, are each on teams that received one of 24 MURI awards totaling $169 million. The research teams include more than one traditional science and engineering discipline to speed the research process.</p><p><g class="gr_ gr_25 gr-alert gr_spell gr_inline_cards gr_run_anim ContextualSpelling ins-del" id="25" data-gr-id="25">Lew is</g> working with a team developing a new class of functional living electronics, which they call <g class="gr_ gr_26 gr-alert gr_spell gr_inline_cards gr_run_anim ContextualSpelling ins-del multiReplace" id="26" data-gr-id="26">livtronics</g>, in which they will determine whether there is a way to engineer and assemble electronic systems based on living materials, such as proteins and bacteria instead of traditional materials, such as silicon. Lew's role is to use fluorescence imaging technology to visualize how electrons are transported through living systems either within the bacterial cell or between bacterial cells in the biofilm. <a href="">The total project received $7.5 million over five years</a>.</p><p>Thimsen is working with a research team investigating how to use dusty plasma, or plasma in which particles are suspended, to make new materials. They will study how to build on what is known about making powders to determine how to make solids, such as ultra-hard and tough ceramics, such as cubic boron nitride. To create the material, researchers are using a low-temperature plasma, which is a <g class="gr_ gr_31 gr-alert gr_gramm gr_inline_cards gr_run_anim Grammar multiReplace" id="31" data-gr-id="31">highly</g> nonequilibrium environment that can provide access to unique and potentially useful states of matter. The five-year project received $6.4 million.</p><p>Vorobeychik is working with a team developing tools to understand and shape online and on-the-ground networks that drive human decision making. It will focus on areas such as international diplomacy, street crime, terrorism, military strategy, financial markets <g class="gr_ gr_35 gr-alert gr_gramm gr_inline_cards gr_run_anim Punctuation only-ins replaceWithoutSep" id="35" data-gr-id="35">and</g> industrial supply chains. The team is using game theory, which is a mathematical way of modeling how different players interact when their interests are potentially in conflict. These players can be organizations, people or computers. The project will apply multi-scale network modeling to the data created by electronic recordkeeping — social media posts, crime statistics, demographic trends <g class="gr_ gr_36 gr-alert gr_gramm gr_inline_cards gr_run_anim Punctuation only-ins replaceWithoutSep" id="36" data-gr-id="36">and</g> other sources. <a href="">The five-year project received $6.25 million</a>.<br/></p><SPAN ID="__publishingReusableFragment"></SPAN><p><br/></p>Beth Miller 2019-03-15T05:00:00ZMatthew Lew, Elijah Thimsen and Yevgeniy Vorobeychik are each on research teams that received one of 24 MURI projects for the Department of Defense.