Skip to main content.
Advanced search >

<< December 2017 >>

Tuesday, December 19, 2017

Biologically plausible deep learning for recurrent spiking neural networks.

Seminar: Redwood Seminar | December 19 | 12-1:30 p.m. | 560 Evans Hall

Shaowei Lin

Neuroscience Institute, Helen Wills

Despite widespread success in deep learning, backpropagation has been criticized for its biological implausibility. To address this issue, Hinton and Bengio have suggested that our brains are performing approximations of backpropagation, and some of their proposed models seem promising. In the same vein, we propose a different model for learning in recurrent neural networks (RNNs), known as...   More >