Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting

TL;DR

This paper introduces a biologically-inspired neural network architecture that learns continuously from data streams with minimal forgetting, avoiding back-propagation and mimicking neurocognitive predictive processing.

Contribution

The proposed Sequential Neural Coding Network is a novel, biologically plausible architecture that reduces catastrophic forgetting in lifelong learning without using back-propagation.

Findings

Significantly less forgetting than standard neural models.

Outperforms previous methods on multiple benchmarks.

Effective in stream-like training scenarios.

Abstract

In lifelong learning systems based on artificial neural networks, one of the biggest obstacles is the inability to retain old knowledge as new information is encountered. This phenomenon is known as catastrophic forgetting. In this paper, we propose a new kind of connectionist architecture, the Sequential Neural Coding Network, that is robust to forgetting when learning from streams of data points and, unlike networks of today, does not learn via the popular back-propagation of errors. Grounded in the neurocognitive theory of predictive processing, our model adapts synapses in a biologically-plausible fashion while another neural system learns to direct and control this cortex-like structure, mimicking some of the task-executive control functionality of the basal ganglia. In our experiments, we demonstrate that our self-organizing system experiences significantly less forgetting compared to standard neural models, outperforming a swath of previously proposed methods, including rehearsal/data buffer-based methods, on both standard (SplitMNIST, Split Fashion MNIST, etc.) and custom benchmarks even though it is trained in a stream-like fashion. Our work offers evidence that emulating mechanisms in real neuronal systems, e.g., local learning, lateral competition, can yield new directions and possibilities for tackling the grand challenge of lifelong machine learning.