We could not locate the page you were looking for.

Below we have generated a list of search results based on the page you were trying to reach.

404 Error
Professor Soatto received his Ph.D. in Control and Dynamical Systems from the California Institute of Technology in 1996; he joined UCLA in 2000 after being Assistant and then Associate Professor of Electrical and Biomedical Engineering at Washington University, and Research Associate in Applied Sciences at Harvard University. Between 1995 and 1998 he was also Ricercatore in the Department of Mathematics and Computer Science at the University of Udine - Italy. He received his D.Ing. degree (highest honors) from the University of Padova- Italy in 1992. His general research interests are in Computer Vision and Nonlinear Estimation and Control Theory. In particular, he is interested in ways for computers to use sensory information (e.g. vision, sound, touch) to interact with humans and the environment. Dr. Soatto is the recipient of the David Marr Prize (with Y. Ma, J. Kosecka and S. Sastry of U.C. Berkeley) for work on Euclidean reconstruction and reprojection up to subgroups. He also received the Siemens Prize with the Outstanding Paper Award from the IEEE Computer Society for his work on optimal structure from motion (with R. Brockett of Harvard). He received the National Science Foundation Career Award and the Okawa Foundation Grant. He is Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) and a Member of the Editorial Board of the International Journal of Computer Vision (IJCV) and Foundations and Trends in Computer Graphics and Vision.
We hope you’re taking some time to relax over the holidays and want to make sure you have plenty of content for when you’re in the mood for a technical binge! December is always slammed with end-of-year events, and this year is no different. We’ve covered some of the month’s events and innovations in our three series this month: NeurIPS, re:Invent, and AI Rewind! re:Invent As always, AWS packed a ton of innovations and announcements into this year’s re:Invent conference. This year, we caught up with none other than Swami Sivasubramanian, VP of AI at AWS, for a re:Invent Roundup to discuss them all. One new offering this year is Amazon SageMaker Feature Store. It turns out that the new service is modeled after the feature store developed by Intuit. In the second episode in this series, we speak with Srivathsan Canchi, head of engineering for the Machine Learning Platform team at Intuit, to dig into the details and backstory. This series also concludes a chat with Edgar Bahilo Rodriguez of Siemens Energy who joins us to talk about Productionalizing Time-Series Workloads, a topic he touched on in his re:Invent talk. NeurIPS As always, this year’s NeurIPS conference featured a ton of great innovation on the research front, and once again we bring those researchers to you with our NeurIPS series. This time around, we spoke with Taco Cohen, ML Researcher at Qualcomm to discuss his work and NeurIPS talk on Natural Graph Networks and video compression using generative models. Another 🔥 conversation in that series is with Charles Isbell, AI researcher and Dean of Engineering at Georgia Tech, who joins us to dive into ML as a Software Engineering Enterprise, the topic of his invited NeurIPS talk exploring the need for a systems approach to tackling big issues in ML like bias. Finally, Aravind Rajeswaran, PhD student at the University of Washington, joins us to talk about his paper, MOReL: Model-Based Offline Reinforcement Learning. AI Rewind Now in its third year, TWIML’s AI Rewind series has become a perennial crowd favorite. The series brings back friends of the show to discuss and explore the year’s most important trends in key topical areas like Machine Learning/Deep Learning, Computer Vision, Natural Language Processing, and Reinforcement Learning. For each topic, we discuss important research and commercial developments of the year and predictions for the year ahead. We just kicked off the AI Rewind series today! Our first episode features my conversation with Pablo Samuel Castro exploring Trends in Reinforcement Learning. Stay tuned for more great shows in this series! We wish you lots of binge-worthy content this holiday season and we’ll see you in the new year!
Today we close out our re:Invent series joined by Edgar Bahilo Rodriguez, Lead Data Scientist in the industrial applications division of Siemens Energy. Edgar spoke at this year's re:Invent conference about Productionizing R Workloads, and the resurrection of R for machine learning and productionalization. In our conversation with Edgar, we explore the fundamentals of building a strong machine learning infrastructure, and how they're breaking down applications and using mixed technologies to build models. We also discuss their industrial applications, including wind, power production management, managing systems intent on decreasing the environmental impact of pre-existing installations, and their extensive use of time-series forecasting across these use cases.
Ken Goldberg is involved in several projects in collaboration with multiple organizations at UC Berkeley, including some technology-based art projects. To hear about all of them, check out the recent TWIML AI Podcast interview, The Third Wave of Robotic Learning with Ken Goldberg. Ever thought you had a good grip on your phone and then watched in slow motion as it fell to the floor? Generally, as humans we’ve learned to gauge how to pick something up, and we usually don’t have to think about the microdecisions and movements involved. But even for us, grasping objects and maintaining stability can be difficult at times. It turns out the seemingly simple task of grasping an object is an even bigger challenge for robots, because they have to learn the physical dexterity grasping requires from zero prior knowledge. So how do we efficiently teach machines this skill? Ken Goldberg is an engineering professor at the University of California, Berkeley where he runs the Laboratory for Automation Science and Engineering (AUTOLAB). The lab is focused on several forms of robotic learning including imitation, deep, and reinforcement learning for a variety of applications spanning surgery to agriculture. One of their major contributions in recent years is the development of the Dexterity Network (Dex-Net), a project that generates datasets for training robust grasping models. The Challenge of Robotic Grasping Researchers have been studying the problem of grasping for decades, but as Ken states, “Robots remain incredibly clumsy today. They’re much better than they were, but industrial arms, if you give them novel objects, they will drop them with a fairly high frequency.” The topic has warranted more attention in recent years with the rapid growth of e-commerce. Training robots to handle packages of various sizes and weights has massive potential for the industry, and large retailers are eager to find a solution, inspiring efforts like the Amazon Picking Challenge in 2017. The act of picking something up sounds fairly simple, but because robots lack physical and perceptual context, it’s a much harder problem than it looks. “Humans and animals… seem to cope very well with a problem like grasping, and interacting with the physical world, because we bring to it a sort of inherent understanding, a deeper understanding about the nature of objects. This is very subtle. I can’t describe this exactly. It’s intuitive to us how to pick things up, but it’s very hard for us to formalize that intuition and give that to a robot.” According to Ken, there are three fundamental elements of uncertainty that make robot grasping extremely difficult: Perception. Understanding the precise geometry of where everything is in a scene can be a complex task. There have been developments in depth sensors like LIDAR, “but they still don’t completely solve this problem because if there’s anything reflective or transparent on the surface, that causes the light to react in unpredictable ways, it doesn’t register as a correct position of where that surface really is.” Adding additional sensors doesn’t help much because they often create contradictions, “[the agent] doesn’t know what to trust” in order to act correctly. Perception is especially important in grasping because “a millimeter or less can make the difference between holding something and dropping it.” Control. The robot has to maintain control of its grasp meaning, “The robot has to now get its gripper to the precise position in space, consistent with what it believes is happening from its sensors.” If the gripper moves slightly or holds it too tight, the object can drop or break. Physics. This has to do with choosing the right place to grasp the object, understanding friction and mass are significant unknowns. To demonstrate how difficult this is, Ken gives the example of pushing a pencil across the table with your finger. We can estimate the pencil’s center of mass, but we ultimately do not know the frictional properties at play. It’s almost impossible to predict the trajectory because even “one microscopic grain of sand, anything under there is going to cause it to behave extremely differently.” What Makes a Grasp “Robust”? For the robustness of a grasp, we want to consider what happens even when the perception, control, and understanding of the physics are slightly off. “If you pick up a glass of wine, for example…Even if the glass isn’t quite where you thought it was, even if your hand isn’t quite where you thought it was, and even if the thing is slippery, you’re still going to be able to pick it up. That’s a robust grasp.” Robust grasps are not uniform because objects vary incredibly. “It turns out that for most objects, there are grasps that are more or less robust. What we’re trying to do is get a robot to learn that quality, that robustness.” “We can generate that by using [physics and mechanics]. Actually it goes all the way back to centuries of beautiful mechanics of understanding the physics and forces and torques, or wrenches, in space that characterize what happens if we know everything. But then what we do is perturb that statistically and if it’s robust it works for all these statistical perturbations with high probability then we say it’s a robust grasp.” Physics vs Statistics and The Third Wave of Robot Learning There’s some debate in the community around the best approaches to robotic learning, which Ken breaks up into three waves of robotic learning. The first wave is the “classic physics” approach which prioritizes traditional understandings of physics in terms of forces, and torques, friction, mass — all that good stuff. The second wave is the more modern, “data-driven approaches that say: ‘Forget about the physics, let’s just learn it from observation purely’” and assume the physics will be learned naturally in the process. Then there’s what Ken advocates for, which is the third wave of robot learning that combines the two fields of thought. The goal is to synthesize the knowledge from both perspectives to optimize performance. However, “figuring out where that combination is is the challenge. And that’s really the story of Dex-Net.” The Dexterity Network The thinking behind Dex-Net was to do for robotics what the development of ImageNet did for computer vision. “ImageNet really transformed machine learning by having a very large data set of labeled images.” By providing a large dataset of labeled images, ImageNet helped spur on the development of deep learning in general, and machine vision in particular. “The question for us was, could we do something analogous in grasping by assembling a very large data set of three-dimensional objects, three-dimensional CAD models, and then labeling them with robust grasps.” To create Dex-Net they used a combination of both physics and statistical-based deep learning techniques. They first applied “that whole first wave [of physics], all that beautiful theory” to loads of simulated models to find which grasps were robust to noise and perturbations. The Use of Depth Sensors to Produce Simulations Pure depth sensors were used to create three-dimensional models and map the objects in space. All other information was stripped away, “I don’t care about the color of things or the texture on things. In fact, that’s a distraction.” Depth sensing makes for nice simulations and perfect models that perturbations and noise could be applied to. In the perfect model, “I have an arrangement of points in space, and then I know when that arrangement corresponds to a successful grasp or not because I’m using the physics and statistical model of the sensor.” After the perturbations, “you have a noisy pattern of points in space, and you know what the true, robust grasp was for that pattern of points…The output is just a scalar or number from zero to one, which is the quality, we call it, the probability that that grasp will succeed.” They’re able to generate millions of these examples fairly quickly (overnight), producing a solid data set to train with. When the machine is shown objects that it has never seen before, it can evaluate the quality of the grasps. “Then what I do is I try a number of different grasps synthetically on that depth map, and it tells me this is the one with highest quality…we consider that the optimal grasp and we execute it. Here’s the thing: It works remarkably well, far better than we thought.” Limitations, Improvements and Applications Those robust examples were then used to train a deep learning system that could generalize to new examples. The system generalized surprisingly well, but as Ken points out, it’s not perfect. The team was able to reach over a 90% success rate, but that was subject to the nature of the objects. “If the objects are all fairly well-behaved like cylinders and cuboids, then it’s fairly easy to do well, but when you have more complex geometries many systems have trouble.” The system still performed well with irregular objects, but did not get close to 100% success. Another limitation is that if you were to change the gripper or sensor, the framework would still apply, but you would have to retrain the system for a new neural network. This is where providing an open dataset and code examples comes in. These can be used to train new grasping models specific to new types of grippers or objects. For an example of Dex-Net in action, check out this video Sam shot at last year’s Siemens Spotlight on Innovation event: In the full interview, Sam and Ken discuss the wide variety of projects he and his lab are working on, from telemedicine to agriculture to art. The conversation on applications picks up at 24:51 in the podcast. Enjoy!
A few weeks ago I had the opportunity to visit Siemens’ Spotlight on Innovation event in Orlando, Florida. The event aimed to bring together industry leaders, technologists, local government leaders, and other innovators for a real-world look at the way technologies like AI, cybersecurity, IoT, digital twin, and smart infrastructure are helping businesses and cities unlock their potential. Siemens put together a nice pre-event program the day before the formal conference which included a tour of their Gamesa Wind Turbine Training Center. We got a peek into the way these machines are assembled, repaired, and managed. As expected, wind turbines are increasingly being fitted with sensors that, when coupled with machine learning algorithms, allow the company to optimize their performance and do predictive maintenance. AI figured prominently into the discussions at the main conference and the highlight for me was Norbert Gaus, head of R&D at Siemens, presenting an overview of the four main AI use cases that the company is interested in: Generative product design Automated product planning Adaptable autonomous machines Real-time simulation and digital twin He covered, though not in much detail, examples in each of these areas. (My Industrial AI ebook is a good reference for more on the opportunities, challenges, and use cases in this space.) Gaus also provided an interesting overview of the systems and software tools the company was building for internal and customer/partner use. These spanned AI-enabled hardware, industry-specific algorithms and services, AI development tools and workflows, pretrained AI models and software libraries, and industrial knowledge graphs. I was able to capture a couple of really interesting conversations with Siemens applied AI research engineers about some of the things the company is up to. Over on Twitter you can check out a short video I made with Siemens engineer Ines Ugalde where she demonstrates a computer vision powered robot arm that she worked on that uses the deep learning based YOLO algorithm for object detection and the Dex-Net grasp quality prediction algorithm designed in conjunction with Ken Goldberg’s AUTOLAB at UC Berkeley, with all inference running in real time on an Intel Movidius VPU. I also had an opportunity to interview Batu Arisoy for Episode 281 of the podcast. Batu is a research manager with the Vision Technologies & Solutions team at Siemens Corporate Technology. Batu’s research focus is solving limited-data computer vision problems. We cover a lot of ground in our conversation, including an interesting use case where simulation and synthetic data are used to recognize spare parts in place, in cases where the part cannot be isolated. “The first way we use simulation is actually to generate synthetic data and one great example use case that we have developed in the past is about spare part recognition. This is a problem if you have a mechanical object that you deploy in the field and you need to perform maintenance and service operations on this mechanical functional object over time. In order to solve this problem what we are working on is using simulation to synthetically generate a training data set for object recognition for large amount of entities. In other words, we synthetically generate images as if these images are collected in real world from an expert and they’re annotated from an expert and this actually comes for free using the simulation. […]We deployed this for the maintenance applications of trains and the main goal is a service engineer goes to the field, he takes his tablet, he takes a picture, then he draws a rectangle box and the system automatically identifies what is the object of interest that the service engineer would like to replace and in order to make the system reliable we have to take into consideration different lighting conditions, texture, colors, or whatever these parts can look like in a real world environment.” There’s a ton of great detail in this conversation. In particular, we dive into quite a few of the details behind how this works, including a couple of methods that they apply which were published in his group’s recent CVPR papers, including Tell Me Where to Look, which introduced the Guided Attention Inference Network, and Learning Without Memorizing. Definitely check out the full interview! Thanks once again to Siemens for hosting this event and for sponsoring my visit, this post, and my conversation with Batu.
Today we're joined by Batu Arisoy, Research Manager with the Vision Technologies & Solutions team at Siemens Corporate Technology. Currently, Batu's research focus is solving limited-data computer vision problems, providing R&D for many of the business units throughout the company. In our conversation, Batu details quite a few of his group's ongoing projects, like an activity recognition project with the Office of Naval Research, and their many CVPR submissions, which include an emulation of a teacher teaching students information without the use of memorization.
Bits & bytes New chips at NIPS. Intel Nervana's forthcoming Neural Network Processor was shown publicly for the first time at this year's NIPS, and the company provided an update on the NNP architecture on its blog. Meanwhile, Nvidia announced the Titan V, its latest GPU based on the Volta architecture. The new and improved GPU boasts 110 teraflops of computing power, an impressive 9x boost over its predecessor, and clocks in at a 'mere' $3k. Nvidia makes healthcare imaging play. Nvidia is taking a crack at medical imaging, an area growing rapidly as healthcare researchers and professionals consider ways to take advantage of AI’s efficiency and power. Nvidia has partnered with GE Healthcare to bring Nvidia's AI platform to its 500,000 imaging devices globally. The company has also partnered with Nuance, whose AI Marketplace for Diagnostic Imaging brings deep learning tools to radiologists. Increasing activity in the AI developer tools space, including an update from Apple's Turi. Interesting profile of Finnish startup Valohai, which offers not only infrastructure-as-a-service for machine learning but also a collaboration platform for data science team workflows. Apple recently released the Turi Create machine learning framework. The tool is designed to simplify the development of custom machine learning models and allow them to be easily exported to Apple’s suite of OSs. The Open Neural Network Exchange format (ONNX) for interoperable neural nets has now reached version 1.0 and is ready for production use, at least according to its backers Microsoft, Facebook and AWS. Learning to play from Zero. Google’s DeepMind recently posted a paper describing AlphaZero, AI software that is capable of learning to play any of three complex games: Chess, Go, or Shogi, achieving superhuman performance in each in under 24 hours of self-play. A single program capable of learning three very different and complex games demonstrates a versatility that is difficult to achieve with modern AI. Google released an AI that analyzes your genome. Genome sequencing has become exponentially more efficient in the 15 years since the first human genome was sequenced. However, analyzing the sequenced genomes is still a tedious process. Google’s DeepVariant is a tool for researchers that can be used to identify regions of interest in a patient's DNA. AI startup funding roundup. Prognos announced it has raised $20.5 million, the startup uses AI algorithms to enable earlier identification of patients who can benefit from enhanced treatment. Legal software firm Luminance announced that it has received $10 millioninvestment to fund its expansion into the U.S. and speed the legal review contracts and other documents with AI. Chinese tech giant Alibaba Holdings has supposedly invested $227M in Beijing-based facial and image recognition firm SenseTime, valuing the firm at $3 billion post-investment. Chattermill announced it raised £600k in funding, the company employs deep algorithms to help companies makes sense of customer feedback. Interesting acquisitions. After getting off to a less than stellar start with the release of their virtual assistant, Bixby, Samsung has acquired Fluenty to help bolster its launch of Bixby 2.0. Siemens has boughtSolido Design Automation, a company using ML algorithms to perfect complex chip design and make sure they’re optimized for power consumption. Sign up for our Newsletter to receive the Bits & Bytes weekly to your inbox.