English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We introduce Error Forward-Propagation, a biologically plausible mechanism topropagate error feedback forward through the network. Architectural constraintson connectivity are virtually eliminated for error feedback in the brain;systematic backward connectivity is not used or needed to deliver errorfeedback. Feedback as a means of assigning credit to neurons earlier in theforward pathway for their contribution to the final output is thought to beused in learning in the brain. How the brain solves the credit assignmentproblem is unclear. In machine learning, error backpropagation is a highlysuccessful mechanism for credit assignment in deep multilayered networks.Backpropagation requires symmetric reciprocal connectivity for every neuron.From a biological perspective, there is no evidence of such an architecturalconstraint, which makes backpropagation implausible for learning in the brain.This architectural constraint is reduced with the use of random feedbackweights. Models using random feedback weights require backward connectivitypatterns for every neuron, but avoid symmetric weights and reciprocalconnections. In this paper, we practically remove this architecturalconstraint, requiring only a backward loop connection for effective errorfeedback. We propose reusing the forward connections to deliver the errorfeedback by feeding the outputs into the input receiving layer. This mechanism,Error Forward-Propagation, is a plausible basis for how error feedback occursdeep in the brain independent of and yet in support of the functionalityunderlying intricate network architectures. We show experimentally thatrecurrent neural networks with two and three hidden layers can be trained usingError Forward-Propagation on the MNIST and Fashion MNIST datasets, achieving$1.90\%$ and $11\%$ generalization errors respectively.

Error Forward-Propagation: Reusing Feedforward Connections to Propagate Errors in Deep Learning