AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks

Suhwan Choi, Myeongho Jeon, Yeonjung Hwang, Jeonglyul Oh, Sungjun Lim, Joonseok Lee, Myungjoo Kang

ICLR 2024 · Architectures and efficiency › RNNs and normalization · approach: Backprop-free credit assignment

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes dictionary contrastive learning as a local-supervision training method that avoids auxiliary networks, aiming for efficient, biologically plausible learning.

Problem

Backpropagation is computationally inefficient and biologically implausible; existing local supervision methods (Local Learning and Forward Learning) either rely on module-wise auxiliary networks or have other limitations.

Approach

Uses a dictionary-based contrastive learning objective to provide local supervision signals without introducing auxiliary networks, per the title; details beyond the title and truncated abstract are not stated.

Experimental setup

Builds on: Local Learning Forward Learning

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy