Forward-Cooperation-Backward (FCB) learning in a Multi-Encoding Uni-Decoding neural network architecture
Prasun Dutta, Koustab Ghosh, Rajat K. De
TL;DR
The paper addresses the biologically plausible learning gap by proposing Forward-Cooperation-Backward (FCB) learning and the MEUD architecture family. It develops four variants—MEUD, MEUD-FF, MEUD-Coop, and MEUD-FF-Coop—to realize forward refinement, latent-layer cooperation, and backward fine-tuning within a reconstruction objective, optimized by ADAM. MEUD-FF-Coop, in particular, achieves superior local-structure preservation as measured by trustworthiness and excels in downstream classification across MNIST, Fashion-MNIST, CIFAR-10, and EMNIST, while also demonstrating faster and smoother convergence. The findings highlight the practical potential of combining forward learning, cooperative latent representations, and backward adjustment for scalable, data-efficient dimensionality reduction and robust analytics. The work advances a biologically inspired alternative to backpropagation, with strong empirical support for improved latent representations and downstream performance.
Abstract
The most popular technique to train a neural network is backpropagation. Recently, the Forward-Forward technique has also been introduced for certain learning tasks. However, in real life, human learning does not follow any of these techniques exclusively. The way a human learns is basically a combination of forward learning, backward propagation and cooperation. Humans start learning a new concept by themselves and try to refine their understanding hierarchically during which they might come across several doubts. The most common approach to doubt solving is a discussion with peers, which can be called cooperation. Cooperation/discussion/knowledge sharing among peers is one of the most important steps of learning that humans follow. However, there might still be a few doubts even after the discussion. Then the difference between the understanding of the concept and the original literature is identified and minimized over several revisions. Inspired by this, the paper introduces Forward-Cooperation-Backward (FCB) learning in a deep neural network framework mimicking the human nature of learning a new concept. A novel deep neural network architecture, called Multi Encoding Uni Decoding neural network model, has been designed which learns using the notion of FCB. A special lateral synaptic connection has also been introduced to realize cooperation. The models have been justified in terms of their performance in dimension reduction on four popular datasets. The ability to preserve the granular properties of data in low-rank embedding has been tested to justify the quality of dimension reduction. For downstream analyses, classification has also been performed. An experimental study on convergence analysis has been performed to establish the efficacy of the FCB learning strategy.