材料日讲座考察人工智能和机器学习的承诺和挑战-新东方前途出国

　　Materials Day talks examine the promises and challenges of AI and machine learning 

　　材料日讲座考察人工智能和机器学习的承诺和挑战

　　The ability to predict and make new materials faster highlights the need for safety, reliability, and accurate data.

　　快速预测和制造新材料的能力突出了对安全性、可靠性和准确数据的需求。 在线咨询

　　Denis Paiste | Materials Research Laboratory

　　丹尼斯·佩斯特材料研究实验室

　　November 5, 2019

　　2019年11月5日

　　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.

　　人工智能和机器学习的承诺和挑战突出了10月9日麻省理工学院材料日研讨会，会上介绍了形成沸石化合物的新方法、更快的药物合成、先进的光学设备等。

　　“Machine learning is having an impact in all areas of materials research,” Materials Research Laboratory Director Carl V. Thompson said.

　　材料研究实验室主任卡尔汤普森说：“机器学习在材料研究的各个领域都产生了影响。

　　“We’re increasingly able to work in tandem with machines to help us decide what materials to make,” said Elsa A. Olivetti, 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.

　　大西洋里奇菲尔德能源研究副教授艾尔莎·奥利维蒂（Elsa A.Olivetti）说：“我们越来越能够与机器协同工作，帮助我们决定制造什么材料。”。她指出，机器学习还指导着如何通过对合成方法的新见解来制作这些材料，在某些情况下（比如机器人系统），还指导着实际制作这些材料。

　　Keynote speaker Brian Storey, director of accelerated materials design and discovery at Toyota Research Institute, spoke about machine learning to advance the switch from 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 atomic engineering using elastic strain and radiation nudging of atoms.

　　主旨演讲人、丰田研究院加速材料设计与发现部主任布赖恩·斯托里谈到了机器学习促进从内燃机向电动汽车的转变，朱丽教授，巴特尔能源联盟核科学与工程教授和材料科学与工程教授谈到原子工程利用原子的弹性应变和辐射轻推。 在线咨询

　　Porous materials

　　多孔材料

　　Olivetti and Rafael Gomez-Bombarelli, 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.

　　OrvieTi和Rafael Gomez Bombarelli，材料处理的丰田助理教授，共同致力于机器学习，以更好地理解多孔材料，称为沸石，由硅和氧化铝形成，具有广泛的用途，从猫砂到石油精炼。

　　“Essentially, the idea is that the pore has the right size to hold organic molecules,” 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. “Some of them can be converted into each other,” he said. “So, 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.”

　　Gomez Bombarelli说：“基本上，这个想法是，孔隙的大小适合容纳有机分子。虽然工程师们只知道这类分子筛约250种，但物理学家可以计算出这些结构可能形成的数十万种方式。“他们中的一些人可以相互转化，”他说。所以，你可以开采一种沸石，将其加压，或加热，它就变成了一种不同的沸石，对特定的应用更有价值

　　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. “Building block theory has some interesting ingredients, but doesn’t quite explain the rules to go from A to B,” Gomez-Bombarelli said.

　　传统的方法是将这些晶体结构解释为积木的组合。然而，当分析沸石转变时，一半以上的时间内，在改变前的原始沸石和改变后的新沸石之间没有共同的积木。“积木理论有一些有趣的成分，但并不完全解释从A到B的规则，”戈麦斯·邦巴雷利说。

　　Graph-based approach

　　基于图的方法

　　Gomez-Bombarelli’s new graph-based approach finds that when each zeolite framework structure is represented as a graph, these graphs match before and after in zeolite transformation pairs. “Some classes of transformations only happen between zeolites that have the same graph,” he said.

　　Gomez-Bombarelli基于图的新方法发现，当每个沸石骨架结构被表示为一个图时，这些图在沸石转化对中前后匹配。他说：“有些种类的转变只发生在具有相同图形的沸石之间。”。 在线咨询

　　This work evolved from Olivetti’s 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. “One of the challenges in learning from the literature is we publish positive examples, we publish data of things that went well,” Olivetti said. In the zeolite community, researchers also publish what doesn’t work. “That’s a valuable dataset for us to learn from,” she said. “What we’ve been able to use this dataset for is to try to predict potential synthesis pathways for making particular types of zeolites.”

　　这项工作是从奥利维蒂对250万篇材料科学期刊文章的数据挖掘发展而来的，这些文章揭示了制造不同无机材料的配方。沸石研究检查了70000篇论文。奥利维蒂说：“从文献中学习的一个挑战是，我们发表正面的例子，发表进展顺利的数据。在沸石社区，研究人员也发表了一些不起作用的东西。她说：“这是一个值得我们学习的宝贵数据集。”。“我们能够使用这个数据集的目的是试图预测制造特定类型沸石的潜在合成途径。”

　　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. “One important challenge in natural language processing is to draw this linked information across a document,” Olivetti explained. “We are trying to build tools that are able to do that linking,” Olivetti says.

　　在早些时候与马萨诸塞大学的同事们的合作中，奥利维蒂开发了一个系统，可以识别出这个大型图书馆中句子中常见的科学词汇和技术，并将类似的发现汇集在一起。奥利维蒂解释说：“在自然语言处理中，一个重要的挑战是在文档中绘制这些链接信息。奥利维蒂说：“我们正在尝试构建能够实现这种链接的工具。

　　AI-assisted chemical synthesis

　　人工智能辅助化学合成

　　Klavs F. Jensen, the Warren K. Lewis Professor of Chemical Engineering and Professor of Materials Science and Engineering, described a chemical synthesis system that combines artificial intelligence-guided processing steps with a robotically operated modular reaction system.

　　沃伦·K·刘易斯化学工程教授、材料科学与工程教授克拉夫斯·F·詹森（Klavs F.Jensen）描述了一种化学合成系统，该系统将人工智能引导的处理步骤与机器人操作的模块化反应系统相结合。 在线咨询

　　For those unfamiliar with synthesis, Jensen explained that “You 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.”

　　对于那些不熟悉合成的人，詹森解释说，“你有反应物，你有反应物，你必须添加的试剂，催化剂等等，才能使反应进行下去，你有中间体，最终你会得到你的产品。”

　　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.

　　詹森说，人工智能系统梳理了1250万个反应，从大约16万个最常用的合成配方中创建了一套规则或库。这种机器学习方法提出了一些处理条件，如在反应中使用什么催化剂、溶剂和试剂。

　　“You 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,” 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.

　　他说：“你可以让这个系统获取它从出版的文献中获得的关于环境等方面的任何信息，你可以利用这些信息来形成一个配方。”。由于还没有足够的数据来通知系统，化学专家仍然需要介入，以指定浓度、流速和工艺堆栈配置，并在将配方发送到机器人系统之前确保安全。

　　The researchers demonstrated this system by predicting synthesis plans for 15 drugs or drug-like molecules — the painkiller lidocaine, for example, and several high blood pressure drugs — and then making them with the system. The flow reactor system contrasts with a batch system. “In order to be able to accelerate the reactions, we use typically much more aggressive conditions than are done in batch — high temperatures and higher pressures,” Jensen says.

　　研究人员通过预测15种药物或类药物分子（例如止痛药利多卡因和几种高血压药物）的合成计划，然后利用该系统进行生产，证明了这一系统。流动式反应器系统与间歇式反应器系统相比。詹森说：“为了能够加速反应，我们通常使用比成批处理更具攻击性的条件——高温和更高的压力。”。 在线咨询

　　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 Science.

　　模块化系统由一个带有可互换反应模块的处理塔和一组不同的试剂组成，这些试剂由机器人连接在一起，用于每次合成。这些发现发表在《科学》杂志上。

　　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.

　　前博士生康纳•W•科利和戴尔•A•托马斯分别建立了计算机辅助合成规划师和流动反应器系统，前博士后贾斯汀•A•M•卢米斯与麻省理工学院本科生研究机会项目的一个大团队、博士生和博士后一起进行了化学研究。詹森还注意到麻省理工学院的同事里贾娜·巴兹莱、威廉·H·格林、A·约翰·哈特、托米·贾科拉和蒂姆·贾米森的贡献。麻省理工学院已经为流体连接的机器人操作申请了专利。建议和优先考虑可能的合成路线的软件套件是开源的，在线版本在ASKCOS网站上。

　　Robustness in machine learning

　　机器学习中的鲁棒性

　　Deep learning systems perform amazingly well on benchmark tasks such as images and natural language processing applications, said Professor Asu Ozdaglar, who heads MIT’s 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.

　　麻省理工学院电子工程与计算机科学系主任阿苏·奥兹达格拉教授说，深度学习系统在图像和自然语言处理应用等基准任务上的表现令人惊讶。然而，研究人员还远未理解这些深度学习系统的工作原理、何时工作以及如何概括。当他们犯错的时候，他们会完全犯错。 在线咨询

　　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, “If you add a little bit of, very little, perturbation, what happens is basically the same classifier thinks that’s an airliner,” Ozdaglar said. “So this is sort of an example where people say machine learning is so powerful, it can make pigs fly,” she said, accompanied by audience laughter. “And this immediately tells us basically we have to go beyond our standard approaches.”

　　Ozdaglar举了一个图像的例子，这个图像有一个最先进的分类器，可以看到一个可爱的猪的图片，并将其识别为猪的图片。但是，奥兹达格拉说：“如果你加上一点，非常小的扰动，所发生的事情基本上就是同一个分类器认为那是一架客机。”。“所以这是一个例子，人们说机器学习是如此强大，它可以让猪飞，”她说，伴随着观众的笑声。“这立即告诉我们，基本上我们必须超越我们的标准方法。”

　　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, “We 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.”

　　一个潜在的解决方案存在于一个称为Minimax或MinMax问题的优化公式中。MinMax公式产生的另一个地方是在生成性对抗网络（generative-departarial network，简称GAN）训练中。Ozdaglar用一个真实汽车图像和假汽车图像的例子解释道：“我们希望这些假图像从与训练集相同的分布中提取，这是通过两个相互竞争的神经网络，一个生成器网络和一个鉴别器网络来实现的。生成器网络从随机噪声中创建这些假图像，鉴别器网络试图将其拉开，以查看这是真是假。”

　　“It’s 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,” she said. The MinMax problem approach has become the backbone of robust training of deep learning systems, she noted.

　　“这基本上是另一个MinMax问题，生成器试图最小化这两个分布之间的距离，假分布和真分布。然后鉴别者试图最大化这一点，”她说。她指出，MinMax问题方法已成为深度学习系统稳健训练的支柱。

　　Ozdaglar added that EECS faculty are applying machine learning to new areas, including health care, citing the work of Regina Barzilay in detecting breast cancer and David Sontag in using electronic medical records for medical diagnosis and treatment.

　　Ozdaglar补充说，EECS学院正在将机器学习应用到包括医疗保健在内的新领域，引用了Regina Barzilay在检测乳腺癌方面的工作和David Sontag在使用电子病历进行医疗诊断和治疗方面的工作。 在线咨询

　　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’s traditional department structure. For example, one idea is to create several cross-departmental teaching groups. “We 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,” she said.

　　去年春天，EECS的本科机器学习课程（6.036）接待了800名学生，并一直有600名或更多的学生注册，使其成为麻省理工学院最受欢迎的课程。新的史蒂芬A施瓦茨曼计算学院提供了一个机会，创造一个比麻省理工学院传统的系结构更具活力和适应性的结构。例如，一个想法是建立几个跨部门的教学小组。她说：“我们设想的是诸如计算、计算科学和工程、计算机社会研究等课程的课程，这些课程是由我们全体学生在麻省理工学院共同教授的。”

　　Optical advantage

　　光学优势

　　Juejun "JJ" Hu, 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’s first prism, work by splitting light, which reduces intensity, but Hu’s 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.

　　材料科学与工程副教授胡俊杰（Juejun“JJ”Hu）详细介绍了他将基于硅芯片的红外光谱仪与新发明的机器学习算法相结合的研究。普通的光谱仪，回到牛顿的第一个棱镜，通过分裂光来工作，这会降低强度，但是胡的版本是在一个探测器上收集所有的光，这样可以保持光的强度，但随后会带来从一次捕获中识别不同波长的问题。

　　“If 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,” Hu said. His new spectrometer architecture, 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. “What 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,” he said.

　　“如果你想解决这个（光谱）分辨率和信噪比之间的折衷，你所要做的就是求助于一种新型的光谱工具，叫做波长复用光谱仪，”胡说。他的新光谱仪结构，被称为数字傅里叶变换光谱仪，在硅芯片上集成了可调谐光开关。该装置通过测量不同光开关设置下的光强度并比较结果来工作。他说：“你得到的基本上是一组线性方程组，它以探测器读数的形式给出了不同波长的光强度的线性组合。”。 在线咨询

　　A prototype device with six switches supports a total of 64 unique optical states, which can provide 64 independent readings. “The advantage of this new device architecture is that the performance doubles every time you add a new switch,” he said. Working with Brando Miranda at the Center for Brains Minds and Machines at MIT, he developed a new algorithm, Elastic D1, that gives a resolution down to 0.2 nanometers and gives an accurate light measurement with only two consecutive measurements.

　　一个带有六个开关的原型设备总共支持64个独特的光学状态，可以提供64个独立的读数。他说：“这种新设备架构的优点是，每次添加新交换机时，性能都会翻倍。”。他与麻省理工学院大脑和机器中心的白兰度·米兰达合作，开发了一种新的算法，弹性D1，它的分辨率可以降低到0.2纳米，并且只需连续两次测量就能得到精确的光测量。

　　“We 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,” 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.

　　“我们相信，这种新型光谱仪结构的硬件和算法之间的独特结合，可以实现从工业过程监测到医学成像等广泛的应用，”胡说。胡教授还将机器学习应用于诸如亚表面等复杂光学介质的研究中，亚表面是一种新型光学器件，其特点是一系列特殊设计的光学天线，可以为入射光增加相位延迟。 在线咨询

　　Poster session winners

　　海报环节获奖者

　　Nineteen MIT postdocs and graduate students gave two-minute talks about their research during a poster session preview. At the Materials Day Poster Session immediately 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.

　　19位麻省理工学院的博士后和研究生在海报预告会上就他们的研究进行了两分钟的演讲。在研讨会之后的材料日海报会议上，获奖者是机械工程研究生艾琳·鲁尼、媒体艺术与科学研究生比安卡·达塔和材料科学与工程博士后迈克尔·乔恩。

　　The Materials Research Laboratory 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.

　　材料研究实验室为教师、工作人员和学生提供跨学科小组，由工业、基金会和政府机构支持，开展材料基础工程研究。研究主题包括能量转换和存储、量子材料、自旋电子学、光子学、金属、集成微系统、材料可持续性、固态电子学、复合氧化物电子特性、生物膜和功能纤维。