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

03/14/2023
by   Lu Yihe, et al.
0

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.

READ FULL TEXT
research
03/15/2023

Lana: A Language-Capable Navigator for Instruction Following and Generation

Recently, visual-language navigation (VLN) – entailing robot agents to f...
research
02/24/2020

The Early Phase of Neural Network Training

Recent studies have shown that many important aspects of neural network ...
research
02/27/2021

A Survey on Physarum Polycephalum Intelligent Foraging Behaviour and Bio-Inspired Applications

In recent years, research on Physarum polycephalum has become more popul...
research
06/24/2020

Topological Insights in Sparse Neural Networks

Sparse neural networks are effective approaches to reduce the resource r...
research
03/25/2022

CNN LEGO: Disassembling and Assembling Convolutional Neural Network

Convolutional Neural Network (CNN), which mimics human visual perception...
research
08/20/2012

Learning sparse messages in networks of neural cliques

An extension to a recently introduced binary neural network is proposed ...

Please sign up or login with your details

Forgot password? Click here to reset