Artificial Neurons and Single-Layer Neural Networks

Внимайте, Sebastian Raschka опубликовал прекрасную статью, подробно раскрывающую начала нейросетей. Замечу в скобочках, код на Python.

Замечательное дополнение к теме нейросетей, раскрытой в курсе ML на Coursera

http://vasnake.blogspot.com/2014/05/neural-networks.html

http://vasnake.blogspot.com/2014/08/blog-post.html

This article offers a brief glimpse of the history and basic concepts of machine learning. We will take a look at the first algorithmically described neural network and the gradient descent algorithm in context of adaptive linear neurons, which will not only introduce the principles of machine learning but also serve as the basis for modern multilayer neural networks in future articles.

Sections

• Introduction
• Artificial Neurons and the McCulloch-Pitts Model
• Frank Rosenblatt's Perceptron
  • The Unit Step Function
  • The Perceptron Learning Rule
  • Implementing the Perceptron Rule in Python
  • Problems with Perceptrons
• Adaptive Linear Neurons and the Delta Rule
  • Gradient Descent
  • The Gradient Descent Rule in Action
  • Online Learning via Stochastic Gradient Descent
• What's Next?
• References

If you are interested to play with the code examples, an IPython notebook version can be found at https://github.com/rasbt/pattern_classification.

http://sebastianraschka.com/Articles/2015_singlelayer_neurons.html

original post http://vasnake.blogspot.com/2015/03/artificial-neurons-and-single-layer.html