Neurogenesis Deep Learning

TL;DR

This paper explores neurogenesis-inspired methods for deep neural networks to improve continuous learning, enabling models to adapt to new data without forgetting previous information, inspired by biological hippocampal neurogenesis.

Contribution

It introduces a novel neurogenesis approach for deep networks, inspired by biological processes, to enhance continuous learning and address stability-plasticity issues.

Findings

Neurogenesis improves model adaptability to new data.

The method maintains performance on previous data while learning new information.

Effective on datasets like MNIST and NIST SD 19.

Abstract

Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing - data processing domains in which humans have long held clear advantages over conventional algorithms. In contrast to biological neural systems, which are capable of learning continuously, deep artificial networks have a limited ability for incorporating new information in an already trained network. As a result, methods for continuous learning are potentially highly impactful in enabling the application of deep networks to dynamic data sets. Here, inspired by the process of adult neurogenesis in the hippocampus, we explore the potential for adding new neurons to deep layers of artificial neural networks in order to facilitate their acquisition of novel information while preserving previously trained data representations. Our results on the MNIST handwritten digit dataset and the NIST SD 19 dataset, which includes lower and upper case letters and digits, demonstrate that neurogenesis is well suited for addressing the stability-plasticity dilemma that has long challenged adaptive machine learning algorithms.