AUTHOR=Wheeldon Adrian , Serb Alexander 

TITLE=A study on the clusterability of latent representations in image pipelines

JOURNAL=Frontiers in Neuroinformatics

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2023.1074653

DOI=10.3389/fninf.2023.1074653

ISSN=1662-5196

ABSTRACT=Latent representations are a necessary component of cognitive artificial intelligence systems.
Here, we investigate the performance of various sequential clustering algorithms on latent
representations generated by autoencoder and convolutional neural network models. Results
show that plain autoencoders produce latent representations which have large inter-cluster
overlaps. Convolutional neural networks are shown to solve this problem, however introduce their
own problems in the context of generalised cognitive pipelines. We also introduce a new algorithm,
called Collage, which brings views and concepts into sequential clustering to bridge the gap
with cognitive artificial intelligence. The algorithm is designed to reduce memory requirements,
numbers of operations (which translate into hardware clock cycles) and thus improve energy,
speed and area performance of an accelerator for running said algorithm.