Factorizers for Distributed Sparse Block Codes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hersche, Michael, Terzic, Aleksandar, Karunaratne, Geethan, Langenegger, Jovin, Pouget, Angéline, Cherubini, Giovanni, Benini, Luca, Sebastian, Abu, Rahimi, Abbas
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913366007611392
author Hersche, Michael
Terzic, Aleksandar
Karunaratne, Geethan
Langenegger, Jovin
Pouget, Angéline
Cherubini, Giovanni
Benini, Luca
Sebastian, Abu
Rahimi, Abbas
author_facet Hersche, Michael
Terzic, Aleksandar
Karunaratne, Geethan
Langenegger, Jovin
Pouget, Angéline
Cherubini, Giovanni
Benini, Luca
Sebastian, Abu
Rahimi, Abbas
contents Distributed sparse block codes (SBCs) exhibit compact representations for encoding and manipulating symbolic data structures using fixed-width vectors. One major challenge however is to disentangle, or factorize, the distributed representation of data structures into their constituent elements without having to search through all possible combinations. This factorization becomes more challenging when SBCs vectors are noisy due to perceptual uncertainty and approximations made by modern neural networks to generate the query SBCs vectors. To address these challenges, we first propose a fast and highly accurate method for factorizing a more flexible and hence generalized form of SBCs, dubbed GSBCs. Our iterative factorizer introduces a threshold-based nonlinear activation, conditional random sampling, and an $\ell_\infty$-based similarity metric. Secondly, the proposed factorizer maintains a high accuracy when queried by noisy product vectors generated using deep convolutional neural networks (CNNs). This facilitates its application in replacing the large fully connected layer (FCL) in CNNs, whereby $C$ trainable class vectors, or attribute combinations, can be implicitly represented by our factorizer having $F$-factor codebooks, each with $\sqrt[\leftroot{-2}\uproot{2}F]{C}$ fixed codevectors. We provide a methodology to flexibly integrate our factorizer in the classification layer of CNNs with a novel loss function. With this integration, the convolutional layers can generate a noisy product vector that our factorizer can still decode, whereby the decoded factors can have different interpretations based on downstream tasks. We demonstrate the feasibility of our method on four deep CNN architectures over CIFAR-100, ImageNet-1K, and RAVEN datasets. In all use cases, the number of parameters and operations are notably reduced compared to the FCL.
format Preprint
id arxiv_https___arxiv_org_abs_2303_13957
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Factorizers for Distributed Sparse Block Codes
Hersche, Michael
Terzic, Aleksandar
Karunaratne, Geethan
Langenegger, Jovin
Pouget, Angéline
Cherubini, Giovanni
Benini, Luca
Sebastian, Abu
Rahimi, Abbas
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
Distributed sparse block codes (SBCs) exhibit compact representations for encoding and manipulating symbolic data structures using fixed-width vectors. One major challenge however is to disentangle, or factorize, the distributed representation of data structures into their constituent elements without having to search through all possible combinations. This factorization becomes more challenging when SBCs vectors are noisy due to perceptual uncertainty and approximations made by modern neural networks to generate the query SBCs vectors. To address these challenges, we first propose a fast and highly accurate method for factorizing a more flexible and hence generalized form of SBCs, dubbed GSBCs. Our iterative factorizer introduces a threshold-based nonlinear activation, conditional random sampling, and an $\ell_\infty$-based similarity metric. Secondly, the proposed factorizer maintains a high accuracy when queried by noisy product vectors generated using deep convolutional neural networks (CNNs). This facilitates its application in replacing the large fully connected layer (FCL) in CNNs, whereby $C$ trainable class vectors, or attribute combinations, can be implicitly represented by our factorizer having $F$-factor codebooks, each with $\sqrt[\leftroot{-2}\uproot{2}F]{C}$ fixed codevectors. We provide a methodology to flexibly integrate our factorizer in the classification layer of CNNs with a novel loss function. With this integration, the convolutional layers can generate a noisy product vector that our factorizer can still decode, whereby the decoded factors can have different interpretations based on downstream tasks. We demonstrate the feasibility of our method on four deep CNN architectures over CIFAR-100, ImageNet-1K, and RAVEN datasets. In all use cases, the number of parameters and operations are notably reduced compared to the FCL.
title Factorizers for Distributed Sparse Block Codes
topic Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2303.13957