Lifelong Learning Starting From Zero
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.
Cite
@article{arxiv.1906.09852,
title = {Lifelong Learning Starting From Zero},
author = {Claes Strannegård and Herman Carlström and Niklas Engsner and Fredrik Mäkeläinen and Filip Slottner Seholm and Morteza Haghir Chehreghani},
journal= {arXiv preprint arXiv:1906.09852},
year = {2019}
}
Comments
To appear in AGI 2019