DevFly: Bio-inspired development of binary connections for locality preserving sparse codes

Tianqi Wei*, Rana Alkhoury Maroun, Qinghai Guo, Barbara Webb

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Neural circuits undergo developmental processes which can be influenced by experience. Here we explore a bio-inspired development process to form the connections in a network used for locality sensitive hashing. The network is a simplified model of the insect mushroom body, which has sparse connections from the input layer to a second layer of higher dimension, forming a sparse code. In previous versions of this model, connectivity between the layers is random. We investigate whether the performance of the hash, evaluated in nearest neighbour query tasks, can be improved by process of developing the connections, in which the strongest input dimensions in successive samples are wired to each successive coding dimension. Experiments show that the accuracy of searching for nearest neighbours is improved, although performance is dependent on the parameter values and datasets used. Our approach is also much faster than alternative methods that have been proposed for training the connections in this model. Importantly, the development process does not impact connections built at an earlier stage, which should provide stable coding results for simultaneous learning in a downstream network.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems
Subtitle of host publication36th Conference on Neural Information Processing Systems
EditorsS. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh
PublisherNeural Information Processing Systems Foundation (NeurIPS)
Pages1-13
Number of pages13
Volume35
ISBN (Electronic)9781713871088
Publication statusPublished - 28 Nov 2022
Event36th Conference on Neural Information Processing Systems - New Orleans, United States
Duration: 28 Nov 20229 Dec 2022

Publication series

NameAdvances in Neural Information Processing Systems
Volume35
ISSN (Print)1049-5258

Conference

Conference36th Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2022
Country/TerritoryUnited States
CityNew Orleans
Period28/11/229/12/22

Fingerprint

Dive into the research topics of 'DevFly: Bio-inspired development of binary connections for locality preserving sparse codes'. Together they form a unique fingerprint.

Cite this