The AI industry’s massive bet on transformer models may not be enough for true AGI

As Big Tech pours unprecedented resources into scaling large language models, critics argue that transformer-based systems ...
IEEE

COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization

Abstract: Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing these ...
TMCnet

MicroAlgo Inc. Develops Quantum Algorithm Technology for Feedforward Neural Networks to Drive Neural Network Revolution

MicroAlgo Inc. (the "Company" or "MicroAlgo") (NASDAQ: MLGO), today announced that they have developed a set of quantum algorithms for feedforward neural networks, breaking through the performance ...
Semiconductor Engineering

The Optical Implementation of Backpropagation (Oxford, Lumai)

A technical paper titled “Training neural networks with end-to-end optical backpropagation” was published by researchers at University of Oxford and Lumai Ltd. “Optics is an exciting route for the ...
eLife

Adjoint propagation of error signal through modular recurrent neural networks for biologically plausible learning

Biologically plausible learning mechanisms have implications for understanding brain functions and engineering intelligent systems. Inspired by the multi-scale recurrent connectivity in the brain, we ...
The New York Times

How ‘Stranger Things’ Defined the Era of the Algorithm

A nostalgic hit built out of vintage pop-culture references captured the “If you liked that, you’ll like this” spirit of Netflix. In the summer of 2016, streaming TV was still figuring itself out.
Hacker

Backprop — The Russian Algorithm the West Claimed as Its Own

Your browser does not support the audio element. The backpropagation algorithm is the cornerstone of modern artificial intelligence. Its significance goes far beyond ...
Scientific Research Publishing

Magoulas, G.D., Vrahatis, M.N. and Androulakis, G.S. (1999) Improving the Convergence of the Backpropagation Algorithm Using Learning Rate Adaptation Methods. Neural ...

ABSTRACT: This paper proposes a unique approach to load forecasting using a fast convergent artificial neural network (ANN) and is driven by the critical need for power system planning. The Mazoon ...
IEEE

Alpha-Backpropagation Algorithm: Probability Estimation for One-Hot and Quasi-One-Hot Teachers

Abstract: This study proposes theories and applications of probabilistic divergences to neural network training. This theory generalizes the cross-entropy method for backpropagation to the ...