neural networks AI Reveals New Possibilities in Matrix Multiplication Inspired by the results of a game-playing neural network, mathematicians have been making unexpected advances on an age-old math ...

Matrix multiplication is a fundamental operation in machine learning, and is one of the most time-consuming, due to the extensive use of multiply-add instructions.

Can artificial intelligence (AI) create its own algorithms to speed up matrix multiplication, one of machine learning’s most fundamental tasks? Today, in a paper published in Nature, DeepMind ...

DeepMind breaks 50-year math record using AI; new record falls a week later AlphaTensor discovers better algorithms for matrix math, inspiring another improvement from afar.

The new version of AlphaZero discovered a faster way to do matrix multiplication, a core problem in computing that affects thousands of everyday computer tasks.

Perfecting that algorithm has been the key to breakthroughs in matrix multiplication efficiency over the past century—even before computers entered the picture.

In 1969 Volker Strassen devised an algorithm for performing matrix multiplication in only n2.81 steps. Since then mathematicians and computer scientists have jockeyed to lower the exponent further.

The algorithm minimizes the number of multiplications for matrix multiplication without commutativity for the special cases p = 1 or 2, n = 1, 2, ⋯ and p = 3, n = 3. It is shown that commutativity ...