A study on the clusterability of latent representations in image pipelines.
A study on the clusterability of latent representations in image pipelines.
复制标题
DOI：
10.3389/fninf.2023.1074653
复制
发表时间：
2023
影响因子：
3.5
通讯作者：
Serb, Alexander
中科院分区：
文献类型：
--
作者：
Wheeldon, Adrian;Serb, Alexander
关键词：
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.
影响因子：
2.9
作者：
Frady, E. Paxon;Kent, Spencer J.;Sommer, Friedrich T.
通讯作者：
Sommer, Friedrich T.
影响因子：
2
作者：
Newson, Alasdair;Almansa, Andres;Ladjal, Said
通讯作者：
Ladjal, Said