Layer Collaboration in the Forward-Forward Algorithm

Guy Lorberbom, Itai Gat, Yossi Adi, Alexander Schwing, Tamir Hazan

Research output: Contribution to journalConference articlepeer-review

Abstract

Backpropagation, which uses the chain rule, is the de-facto standard algorithm for optimizing neural networks nowadays. Recently, as an alternative, the Forward-Forward algorithm had been proposed. The algorithm optimizes neural nets layer-by-layer, without propagating gradients throughout the network. Although such an approach has several advantages over back-propagation and shows promising results, the fact that each layer is being trained independently limits the optimization process. Specifically, it prevents the network’s layers from collaborating to learn complex and rich features. In this work, we study layer collaboration in the forward-forward algorithm. We show that the current version of the forward-forward algorithm is suboptimal when considering information flow in the network, resulting in a lack of collaboration between layers of the network. We propose an improved version that supports layer collaboration to better utilize the network structure, while not requiring any additional assumptions or computations. We empirically demonstrate the efficacy of the proposed version when considering both information flow and objective metrics. Additionally, we provide a theoretical motivation for the proposed method, inspired by functional entropy theory.

Original languageEnglish
Pages (from-to)14141-14148
Number of pages8
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume38
Issue number13
DOIs
StatePublished - 25 Mar 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: 20 Feb 202427 Feb 2024

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Layer Collaboration in the Forward-Forward Algorithm'. Together they form a unique fingerprint.

Cite this