We compared the efficiency of the FlyHash model, an insect-inspired sparse neural network (Dasgupta et al., 2017), to similar but non-sparse models in an embodied navigation task. This requires a model to control steering by comparing current visual inputs to memories stored along a training route. We concluded the FlyHash model is more efficient than others, especially in terms of data encoding.
Cite
@article{arxiv.2303.08109,
title = {Vision-based route following by an embodied insect-inspired sparse neural network},
author = {Lu Yihe and Rana Alkhoury Maroun and Barbara Webb},
journal= {arXiv preprint arXiv:2303.08109},
year = {2023}
}
Comments
8 pages, 4 figures; work-in-progress submission, accepted as a poster at ICLR 2023 Workshop on Sparsity in Neural Networks; non-archival