# Lifelong Learning Starting From Zero

## TL;DR

This paper introduces a biologically inspired deep neural network model for lifelong learning that starts from zero and evolves through expansion, generalization, forgetting, and backpropagation, demonstrating improved accuracy and efficiency.

## Contribution

It presents a novel lifelong learning neural network model that develops from scratch using four neuroplasticity-inspired rules, differing from traditional fixed-structure models.

## Key findings

- Better accuracy compared to other models
- More energy-efficient learning process
- Enhanced versatility in tasks

## Abstract

We present a deep neural-network model for lifelong learning inspired by several forms of neuroplasticity. The neural network develops continuously in response to signals from the environment. In the beginning, the network is a blank slate with no nodes at all. It develops according to four rules: (i) expansion, which adds new nodes to memorize new input combinations; (ii) generalization, which adds new nodes that generalize from existing ones; (iii) forgetting, which removes nodes that are of relatively little use; and (iv) backpropagation, which fine-tunes the network parameters. We analyze the model from the perspective of accuracy, energy efficiency, and versatility and compare it to other network models, finding better performance in several cases.