Random feedback weights support learning in deep neural networks
作者： Daniel Cownden , Colin J. Akerman , Douglas B. Tweed , Timothy P. Lillicrap
DOI:
关键词:
摘要: … a surprisingly simple algorithm for deep learning, which … Our demonstration provides a plausible basis for how a neuron can be … to preceding layers of a neural network. a, The backprop …
harvard.edu
arxiv-vanity.com
arxiv.org参考文章(20)
Volodymyr Mnih, CUDAMat: a CUDA-based matrix class for Python ,(2009)
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams, Learning representations by back-propagating errors Nature. ,vol. 323, pp. 696- 699 ,(1988) , 10.1038/323533A0
Robert Urbanczik, Walter Senn, Reinforcement learning in populations of spiking neurons Nature Neuroscience. ,vol. 12, pp. 250- 252 ,(2009) , 10.1038/NN.2264
Francis Crick, The recent excitement about neural networks Nature. ,vol. 337, pp. 129- 132 ,(1989) , 10.1038/337129A0
Pietro Mazzoni, Richard A Andersen, Michael I Jordan, None, A more biologically plausible learning rule for neural networks. Proceedings of the National Academy of Sciences of the United States of America. ,vol. 88, pp. 4433- 4437 ,(1991) , 10.1073/PNAS.88.10.4433
Stork, Is backpropagation biologically plausible international joint conference on neural network. pp. 241- 246 ,(1989) , 10.1109/IJCNN.1989.118705
H.Sebastian Seung, Learning in spiking neural networks by reinforcement of stochastic synaptic transmission. Neuron. ,vol. 40, pp. 1063- 1073 ,(2003) , 10.1016/S0896-6273(03)00761-X
D. Van Essen, C. Anderson, D. Felleman, Information processing in the primate visual system - An integrated systems perspective Science. ,vol. 255, pp. 419- 423 ,(1992) , 10.1126/SCIENCE.1734518
Timothy P. Lillicrap, Stephen H. Scott, Preference Distributions of Primary Motor Cortex Neurons Reflect Control Solutions Optimized for Limb Biomechanics Neuron. ,vol. 77, pp. 168- 179 ,(2013) , 10.1016/J.NEURON.2012.10.041
Geoffrey E Hinton, Ruslan R Salakhutdinov, Reducing the Dimensionality of Data with Neural Networks Science. ,vol. 313, pp. 504- 507 ,(2006) , 10.1126/SCIENCE.1127647