Biologically Inspired Feedforward Supervised Learning for Deep Self-Organizing Map Networks
This addresses the need for more human-like, association-based learning in neural networks, but appears incremental as it builds on existing self-organizing map concepts.
The authors tackled the problem of supervised learning without backpropagation by proposing a biologically inspired feedforward method, achieving validation on the MNIST dataset.
In this study, we propose a novel deep neural network and its supervised learning method that uses a feedforward supervisory signal. The method is inspired by the human visual system and performs human-like association-based learning without any backward error propagation. The feedforward supervisory signal that produces the correct result is preceded by the target signal and associates its confirmed label with the classification result of the target signal. It effectively uses a large amount of information from the feedforward signal, and forms a continuous and rich learning representation. The method is validated using visual recognition tasks on the MNIST handwritten dataset.