15. Červenec 2019
Raia Hadsell, a senior research scientist at DeepMind, has worked on deep learning and robotics problems for over 10 years. Her early research developed the approach of learning embeddings using Siamese networks, which has been used extensively for representation learning. After completing a PhD with Yann LeCun, which featured a self-supervised deep learning vision system for a mobile robot, her research continued at Carnegie Mellon’s Robotics Institute and SRI International, and in early 2014 she joined DeepMind in London to study artificial general intelligence. Her current research focuses on the challenge of continual learning for AI agents and robots. While deep RL algorithms are capable of attaining superhuman performance on single tasks, they often cannot transfer that performance to additional tasks, especially if experienced sequentially. She has proposed neural approaches such as policy distillation, progressive nets, and elastic weight consolidation to solve the problem of catastrophic forgetting for agents and robots.
The ACM Special Interest Group on Genetic and Evolutionary Computation (SIGEVO) aims to promote and disseminate in academia, industry, and society the principles, techniques and applications of Genetic and Evolutionary Computation as well as other bio-inspired methods. Evolutionary algorithms address discrete and continuous optimization, modeling and machine learning. They have achieved human competitive results and solved complex, challenging problems in a myriad of real world domains. Evolutionary computation also includes the study of complex artificial evolutionary systems and processes. SIGEVO operates the annual Genetic and Evolutionary Computation Conference (GECCO) and the biannual workshop on the Foundations of Genetic Algorithms (FOGA). Sigevo provides support for student participation in the activities of the organization, supports other educational efforts and sponsors other specialized conferences and events. Members include academic and industrial researchers, educators and practitioners, software developers, artists, and students.
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Prezentace na podobné téma, kategorii nebo přednášejícího