Lifelong Learning Starting From Zero
This addresses the challenge of lifelong learning for AI systems, though it appears incremental as it builds on existing neuroplasticity concepts.
The paper tackles the problem of lifelong learning by proposing a deep neural network model that starts with no nodes and develops continuously through neuroplasticity-inspired rules, achieving better performance in accuracy, energy efficiency, and versatility compared to other models in several cases.
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.