Constrained parameter inference as a principle for learning

N Ahmad, E Schrader, M van Gerven - arXiv preprint arXiv:2203.13203, 2022 - arxiv.org
Learning in neural networks is often framed as a problem in which targeted error signals are
directly propagated to parameters and used to produce updates that induce more optimal …

Efficient Target Propagation by Deriving Analytical Solution

Y Bao, T Shibuya, I Sato, R Kawakami… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Exploring biologically plausible algorithms as alternatives to error backpropagation (BP) is a
challenging research topic in artificial intelligence. It also provides insights into the brain's …