"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
research
09/09/2013

Application of Artificial Neural Networks in Estimating Participation in Elections

It is approved that artificial neural networks can be considerable effec...
research
05/06/2022

Stochastic resonance neurons in artificial neural networks

Many modern applications of the artificial neural networks ensue large n...
research
08/11/2020

Supersymmetric Artificial Neural Network

The “Supersymmetric Artificial Neural Network” hypothesis (with the nove...
research
09/07/2020

Modeling protoplanetary disk SEDs with artificial neural networks: Revisiting the viscous disk model and updated disk masses

We model the spectral energy distributions (SEDs) of 23 protoplanetary d...
research
04/22/2021

Synchronization of Tree Parity Machines using non-binary input vectors

Neural cryptography is the application of artificial neural networks in ...
research
11/06/2019

Correlated Feature Selection for Tweet Spam Classification using Artificial Neural Networks

Identification of spam messages is a very challenging task for social ne...
research
07/25/2021

Denoising and Segmentation of Epigraphical Scripts

This paper is a presentation of a new method for denoising images using ...

Please sign up or login with your details

Forgot password? Click here to reset