Learning Using a Single Forward Pass

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Somasundaram, Aditya, Mishra, Pushkal, Borthakur, Ayon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908393734668288
author Somasundaram, Aditya
Mishra, Pushkal
Borthakur, Ayon
author_facet Somasundaram, Aditya
Mishra, Pushkal
Borthakur, Ayon
contents We propose a learning algorithm to overcome the limitations of traditional backpropagation in resource-constrained environments: Solo Pass Embedded Learning Algorithm (SPELA). SPELA operates with local loss functions to update weights, significantly saving on resources allocated to the propagation of gradients and storing computational graphs while being sufficiently accurate. Consequently, SPELA can closely match backpropagation using less memory. Moreover, SPELA can effectively fine-tune pre-trained image recognition models for new tasks. Further, SPELA is extended with significant modifications to train CNN networks, which we evaluate on CIFAR-10, CIFAR-100, and SVHN 10 datasets, showing equivalent performance compared to backpropagation. Our results indicate that SPELA, with its features such as local learning and early exit, is a potential candidate for learning in resource-constrained edge AI applications.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09769
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Using a Single Forward Pass
Somasundaram, Aditya
Mishra, Pushkal
Borthakur, Ayon
Artificial Intelligence
We propose a learning algorithm to overcome the limitations of traditional backpropagation in resource-constrained environments: Solo Pass Embedded Learning Algorithm (SPELA). SPELA operates with local loss functions to update weights, significantly saving on resources allocated to the propagation of gradients and storing computational graphs while being sufficiently accurate. Consequently, SPELA can closely match backpropagation using less memory. Moreover, SPELA can effectively fine-tune pre-trained image recognition models for new tasks. Further, SPELA is extended with significant modifications to train CNN networks, which we evaluate on CIFAR-10, CIFAR-100, and SVHN 10 datasets, showing equivalent performance compared to backpropagation. Our results indicate that SPELA, with its features such as local learning and early exit, is a potential candidate for learning in resource-constrained edge AI applications.
title Learning Using a Single Forward Pass
topic Artificial Intelligence
url https://arxiv.org/abs/2402.09769