"This item is a glaxefw, and this is a glaxuzb": Compositionality Through Language Transmission, using Artificial Neural Networks

01/27/2021 ∙ by Hugh Perkins, et al. ∙ 0

We propose an architecture and process for using the Iterated Learning Model ("ILM") for artificial neural networks. We show that ILM does not lead to the same clear compositionality as observed using DCGs, but does lead to a modest improvement in compositionality, as measured by holdout accuracy and topologic similarity. We show that ILM can lead to an anti-correlation between holdout accuracy and topologic rho. We demonstrate that ILM can increase compositionality when using non-symbolic high-dimensional images as input.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 9

Code Repositories

neural-ilm

Code for https://arxiv.org/abs/2101.11739


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.