# Vision-based route following by an embodied insect-inspired sparse neural network

arXiv: https://arxiv.org/abs/2303.08109 · HTML: https://mlsanity.com/paper/2303.08109/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 9 references that are in the map.
- First posted on arXiv 14 Mar 2023.

## Builds on (most cited first, 2 of 2)

- [iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes](https://mlsanity.com/paper/2012.02924/) (2020)
- [Expressivity of expand-and-sparsify representations](https://mlsanity.com/paper/2006.03741/) (2020)

## Abstract (arXiv)

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.