arXiv (All)
open access
Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Hardware-Validated Benchmarking Study of Forward-Only Algorithms
Backpropagation (BP) powers modern deep learning, but it must hold every activation in memory until a global backward sweep consumes it, and that sweep locks each layer until the one above has finished. Forward-only algorithms, from Hinton's Forward-Forward (FF) through Cascaded Forward (CaFo) to Mo
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- PyTorch Distributed: Experiences on Accelerating Data Parallel Training#130777
- From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon#1341750
- FFR: Forward-Forward Learning for Regression#1218368
- The Price of Locality: Why Forward-Forward Underperforms Backpropagation?#1117952
- The Ups and Downs of Backprop Weights#1037237
Record · ID 1327284
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive