A study on the clusterability of latent representations in image pipelines

Latent representations are a necessary component of cognitive artificial intelligence (AI) systems. Here, we investigate the performance of various sequential clustering algorithms on latent representations generated by autoencoder and convolutional neural network (CNN) models. We also introduce a n...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in neuroinformatics 2023-02, Vol.17, p.1074653-1074653
Main Authors: Wheeldon, Adrian, Serb, Alexander
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
autoencoders
Clustering
Cognitive ability
convolutional neural networks
Datasets
Experiments
Machine learning
Neural networks
Neuroscience
Semantics
symbolics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Latent representations are a necessary component of cognitive artificial intelligence (AI) systems. Here, we investigate the performance of various sequential clustering algorithms on latent representations generated by autoencoder and convolutional neural network (CNN) models. We also introduce a new algorithm, called Collage, which brings views and concepts into sequential clustering to bridge the gap with cognitive AI. 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. Results show that plain autoencoders produce latent representations which have large inter-cluster overlaps. CNNs are shown to solve this problem, however introduce their own problems in the context of generalized cognitive pipelines.
ISSN:1662-5196
1662-5196
DOI:10.3389/fninf.2023.1074653