Iterative temporal differencing with random synaptic feedback weights support error backpropagation for deep learning
Year: 2019
Type: preprint
Abstract: This work shows that a differentiable activation function is not necessary any more for error backpropagation. The derivative of the activation function can be replaced by an iterative temporal differencing using fixed random feedback alignment. Using fixed random synaptic feedback alignment with an iterative temporal differencing is transforming the traditional error backpropagation into a more biologically plausible approach for learning deep neural network architectures. This can be a big step toward the integration of STDP-based error backpropagation in deep learning.
Source: arXiv (Cornell University)
Author: Dargazany, Aras R.
Institution: University of Rhode Island
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2958540581