Pattern recognition—such as that used in image recognition, speech recognition and machine translation—has been the primary focus of the last decade’s progress in artificial intelligence. But intelligence fundamentally requires more than mere pattern recognition: It also requires the ability to achieve goal-oriented behaviors.
Two new methods, deep reinforcement learning and deep imitation learning, provide paradigms for learning goal-oriented behaviors and have shown great promise in recent research. These approaches have demonstrated remarkable success in learning to play video games, learning to control simulated and real robots, mastering the classical game of Go and automation of character animation.
In this talk I will describe the ideas underlying these advances, and their current capabilities and limitations, with a focus on practical applications. I’ll explore the characteristics that have unlocked important new use cases (e.g. AI robotic automation in warehouses) while others (e.g., self-driving cars) remain AI-bottlenecked. I’ll also highlight important areas where significant breakthroughs are still needed.
See Pieter Abbeel and many other expert speakers at the 2021 Embedded Vision Summit!
Professor Pieter Abbeel is Director of the Berkeley Robot Learning Lab and Co-Director of the Berkeley Artificial Intelligence (BAIR) Lab. Abbeel’s research strives to build ever more intelligent systems. His lab pushes the frontiers of deep reinforcement learning, deep imitation learning, deep unsupervised learning, transfer learning, meta-learning and learning to learn and studies the influence of AI on society. His lab also investigates how AI can advance other science and engineering disciplines. Abbeel’s Intro to AI class has been taken by over 100,000 students through edX, and his deep reinforcement learning and deep unsupervised learning materials are standard references for AI researchers.
Abbeel has founded three companies: Gradescope (AI to help teachers with grading homework and exams), Covariant (AI for robotic automation of warehouses and factories) and Berkeley Open Arms (low-cost, highly capable 7-dof robot arms). He advises many AI and robotics start-ups, and is a sought-after speaker worldwide for C-suite sessions on AI future and strategy.
Abbeel earned his M.S. in Electrical Engineering from KU Leuven, Belgium and his Ph.D. from Stanford, where his advisor was Andrew Ng. He has received numerous awards and honors, including the Presidential Early Career Award for Scientists and Engineers, the NSF Faculty Early Career Award, being named a Top 35 Innovator Under 35 by MIT Technology Review and awards for excellence in teaching and mentoring. His papers have earned Best Paper awards at the ICLR, ICRA, NIPS and ICML conferences. His work is frequently featured in the press, including the New York Times, Wall Street Journal, BBC, Rolling Stone, Wired and Tech Review.
They’re here!!! 🙌🏼1st round of speakers just added to the Summit program😃 These are the experts working day-in and day-out creating solutions to real-world problems using #ComputerVision and edge #AI. 80+ more speakers to come. Speakers & sessions: https://embeddedvisionsummit.com/speakers/
Join us Thur—say 9 am PT— for a free in-depth tutorial by @zach_shelby & @dansitu of @EdgeImpulse? Topics include assembling datasets, designing and training highly accurate models, imple... (Live demos and Q&A) Info & all topics: https://bit.ly/3quzTm3 #machinelearningengineer