paper-with-me

Papers

Iterative temporal differencing with random synaptic feedback weights support error backpropagation for deep learning

2019-07-15 · Aras R. Dargazany

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.

📄 PDF Abstract BibTeX arXiv:1907.07255

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Iterative temporal differencing with fixed random feedback alignment support spike-time dependent plasticity in vanilla backpropagation for deep learning

2018-01-01 · ICLR 2018 1 · Aras Dargazany, Kunal Mankodiya

In vanilla backpropagation (VBP), activation function matters considerably in terms of non-linearity and differentiability. Vanishing gradient has been an important problem related to the bad choice of activation functio…

Deep Learning

Online Learning Of Neural Computations From Sparse Temporal Feedback

2021-12-01 · NeurIPS 2021 12 · Lukas Braun, Tim Vogels

Neuronal computations depend on synaptic connectivity and intrinsic electrophysiological properties. Synaptic connectivity determines which inputs from presynaptic neurons are integrated, while cellular properties determ…

Neuromorphic Deep Learning Machines

2016-12-16 · Emre Neftci, Charles Augustine, Somnath Paul, Georgios Detorakis

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasi…

Deep Learning

Contrastive Hebbian Learning with Random Feedback Weights

2018-06-19 · Georgios Detorakis, Travis Bartley, Emre Neftci

Neural networks are commonly trained to make predictions through learning algorithms. Contrastive Hebbian learning, which is a powerful rule inspired by gradient backpropagation, is based on Hebb's rule and the contrasti…

Closed-Form Feedback-Free Learning with Forward Projection

2025-01-27 · Robert O'Shea, Bipin Rajendran

State-of-the-art methods for backpropagation-free learning employ local error feedback to direct iterative optimisation via gradient descent. In this study, we examine the more restrictive setting where retrograde commun…

Few-Shot LearningForm