Symposium: Brains, Minds and Machines - Surya Ganguli
490
20.4
Microsoft Research334 тыс
Следующее
06.06.16 – 1 23513:57Популярные
300 дней – 2 5693:17
Опубликовано 6 июня 2016, 23:11
Towards Glimpses of a New Science of Brains, Minds and Machines: Weaving Together Physics, Computer Science, and Neurobiology.
Our neural circuits exploit the laws of physics to perform computations in ways that are fundamentally different from traditional computers designed by these same neural circuits. To eradicate this irony, we must develop a new science of brains, minds and machines that seamlessly weaves together physics, computation and neurobiology to both elucidate the design principles governing neural systems, and instantiate these principles in physical devices. We will discuss several glimpses in such a direction, including: (1) understanding the speed with which both infants and deep neural circuits learn hierarchical structure, (2) exploiting the geometry of high dimensional error surfaces to speed up learning, (3) exploiting ideas from non-equilibrium statistical mechanics to circumvent credit-assignment and mixing time problems to learn very deep stochastic generative models, and (4) delineating fundamental theoretical limits on the energy, speed and accuracy of communication by any physically implementable device.
research.microsoft.com
Our neural circuits exploit the laws of physics to perform computations in ways that are fundamentally different from traditional computers designed by these same neural circuits. To eradicate this irony, we must develop a new science of brains, minds and machines that seamlessly weaves together physics, computation and neurobiology to both elucidate the design principles governing neural systems, and instantiate these principles in physical devices. We will discuss several glimpses in such a direction, including: (1) understanding the speed with which both infants and deep neural circuits learn hierarchical structure, (2) exploiting the geometry of high dimensional error surfaces to speed up learning, (3) exploiting ideas from non-equilibrium statistical mechanics to circumvent credit-assignment and mixing time problems to learn very deep stochastic generative models, and (4) delineating fundamental theoretical limits on the energy, speed and accuracy of communication by any physically implementable device.
research.microsoft.com
Свежие видео
5 дней – 2 7002:08
11 дней – 1 0675:05
12 дней – 9310:05
13 дней – 62624:52Случайные видео
18 дней – 030:58
07.03.23 – 100 09734:33
30.10.22 – 16 0220:42
07.08.22 – 79 10814:43
29.08.21 – 6 1740:52
19.04.20 – 77 49111:53
4 часа – 13625:01
1 день – 4712:39
2 дня – 218 8677:38
2 дня – 26019:39
6 дней – 4350:29
