What are the main common deep learning algorithms?
Three common algorithms for deep learning are: convolutional neural network, recurrent neural network, and generative adversarial network.
Convolutional Neural Networks (CNN) are a type of feedforward neural networks (Feedforward Neural Networks) that include convolutional calculations and have a deep structure. They are one of the representative algorithms of deep learning.
Recurrent Neural Network (RNN) is a type of recursive neural network that takes sequence data as input, performs recursion in the evolution direction of the sequence, and has all nodes (recurrent units) connected in a chain.
Generative Adversarial Networks (GAN) is a deep learning model and an unsupervised learning algorithm that has been very popular in the past two years.
Google Artificial Intelligence Writing Project: Neural Network Pseudo-Original
How to calculate the weight and offset between the top hidden layer and the output layer in a deep neural network?
It must be the training method. The weights of the neural network are not artificially given by writing cats .
Instead, the training set (including input and output) is used for training. Training with the training set is called an epoch. It usually takes many epochs. The purpose is to make the error between the target and the training result (usually using the mean square error) as small as one given. a certain threshold.
The above mentioned are supervised learning methods, and there are also unsupervised learning methods.
Why does the bp algorithm not work on deep neural networks?
BP algorithm is a typical algorithm for traditional training of multi-layer networks. In fact, for networks with only a few layers, this training method is already very unsatisfactory and no further calculations are required.