Trainable hardware for dynamical computing using error backpropagation through physical media.
Trainable hardware for dynamical computing using error backpropagation through physical media.
复制标题
DOI:
10.1038/ncomms7729
复制
发表时间:
2015-03-24
影响因子:
16.6
通讯作者:
Bienstman, Peter
中科院分区:
文献类型:
--
作者:
Hermans, Michiel;Burm, Michael;Van Vaerenbergh, Thomas;Dambre, Joni;Bienstman, Peter
Neural networks are currently implemented on digital Von Neumann machines, which do not fully leverage their intrinsic parallelism. We demonstrate how to use a novel class of reconfigurable dynamical systems for analogue information processing, mitigating this problem. Our generic hardware platform for dynamic, analogue computing consists of a reciprocal linear dynamical system with nonlinear feedback. Thanks to reciprocity, a ubiquitous property of many physical phenomena like the propagation of light and sound, the error backpropagation—a crucial step for tuning such systems towards a specific task—can happen in hardware. This can potentially speed up the optimization process significantly, offering important benefits for the scalability of neuro-inspired hardware. In this paper, we show, using one experimentally validated and one conceptual example, that such systems may provide a straightforward mechanism for constructing highly scalable, fully dynamical analogue computers. Machine learning systems use algorithms that can interpret data to make improved decisions. Hermans et al. develop a physical scheme for a computing system based on recurrent neural networks that physically implements the error backpropagation algorithm, thus performing its own training process.
登录
查看更多内容
影响因子:
3.8
作者:
Larger, L.;Soriano, M. C.;Fischer, I.
通讯作者:
Fischer, I.
影响因子:
16.6
作者:
Vandoorne, Kristof;Mechet, Pauline;Bienstman, Peter
通讯作者:
Bienstman, Peter
影响因子:
12.9
作者:
Lukosevicius, Mantas;Jaeger, Herbert
通讯作者:
Jaeger, Herbert
影响因子:
16.6
作者:
通讯作者:
--
影响因子:
20.6
作者:
CAULFIELD, HJ;KINSER, J;ROGERS, SK
通讯作者:
ROGERS, SK