深度学习概述.md

Concept

Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence.

Deep Learning is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text.

The ultimate goal of Deep Learning is to build machines that learn to think and perceive the world as humans do.

Deep Learning has been achieving state-of-the-art results in various domains such as computer vision, speech recognition, natural language processing, and audio recognition.

Origin & Development

1st Gen Neural Networks (1958~1969)

Originated from the MCP model in 1943, the first generation of neural networks was developed to mimic the way the human brain works.

2nd Gen Neural Networks (1986~1998)

In 1986, The backpropagation algorithm was introduced by Hinton to train multi-layer perceptrons (MLP). He also introduced the sigmoid activation function to replace the step function, which was used in the first generation of neural networks.

Spring of Statistical Learning (1986~2006)

3rd Gen Neural Networks (2006~)