Turing Game by scch { }

To the Game

First Modern Backpropagation ​

by | Aug 21, 2024 | Mathematics

In his 1976 paper “Taylor Expansion of the Accumulated Rounding Error,” S. Linnainmaa presented a novel approach for addressing rounding errors in numerical calculations through the use of Taylor series expansion. By systematically expanding the rounding...

First version of dropout

by | Jun 30, 1990 | Mathematics

The 1990 paper “A Stochastic Version of the Delta Rule” by Stephen J. Hanson introduces a modified version of the delta rule incorporating synaptic noise into the weight update process of neural networks. This stochastic approach, termed the Stochastic...

First Modern Backpropagation

by | Jan 22, 1976 | Mathematics

In his 1976 paper “Taylor Expansion of the Accumulated Rounding Error,” S. Linnainmaa presented a novel approach for addressing rounding errors in numerical calculations through the use of Taylor series expansion. By systematically expanding the rounding...

Ising’s model

by | Jan 1, 1970 | Mathematics

The first non-learning recurrent neural network (RNN) architecture, known as the Ising model or Lenz-Ising model, was introduced and analyzed by physicists Ernst Ising and Wilhelm Lenz in the 1920s. This model was originally developed to understand ferromagnetism in...

Adaptive Ising Model

by | Jan 1, 1970 | Mathematics

In his 1972 paper “Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements,” S. -I. Amari proposed a pioneering approach to pattern recognition and sequence learning through the use of self-organizing neural networks. These...

Linear regression

by | Jan 1, 1970 | Mathematics

Linear regression is still a frequently used approximation for explaining linear dependencies between phenomena. It is often the first out-of-shelf method in various fields, such as econometrics, biology, engineering, and social sciences, due to its simplicity and...