1 Deep Learning - Introduction to Neural Networks
Deep Learning (also known as Deep Structured Learning, Hierarchical Learning or Deep Machine Learning) is a collection of algorithms and a branch of machine learning.
Deep learning methods have shown amazing accuracy in recent years in areas such as conversation recognition, image recognition, and object detection.
However, the term "deep learning" is very old. It was proposed by Dechter in the field of machine learning in 1986, and then introduced into artificial neural networks by Aizenberg et al. in 2000. Now, Alex Krizhevsky has attracted everyone's attention after winning the ImageNet competition in 2012 using a convolutional network structure.
The father of convolutional networks: Yann LeCun
Deep learning demo
Link: http://playground.tensorflow.org
2 Responsibilities of each layer of deep learning
Each layer of the neural network is responsible for:
Layer 1: Responsible for identifying colors and simple textures
Layer 2: Some neurons can recognize more detailed textures, cloth patterns, engravings, leaf patterns, etc.
Layer 3: Some neurons are responsible for sensing yellow candlelight, highlight, firefly, egg yellow, etc. in the dark night.
Layer 4: Some neurons recognize the presence of cute dog faces, pet shapes, cylindrical objects, seven-star ladybugs, etc.
Layer 5: Some neurons are responsible for identifying flowers, black-eyed animals, birds, keyboards, prototype roofs, etc.
