Article From:https://www.cnblogs.com/ltcblog/p/9496572.html

The first chapter introduces the course.
Introduce the background of machine learning, introduce the background of tensorflow, introduce the course python, numpy, virtualenv and other pre-learning content, install tensorflow
1-1 Guidance
1-2 course arrangement
1-3 Deep learning background
1-5 development environment
1-6 virtualenvbrief introduction
1-7 pythonCommon operation
1-8 numpyCommon operation 01
1-9 numpyCommon operation 02
1-10 MacInstallation of the next TensorFlow
1-11 WindowsInstallation of the next TensorFlow
1-12 ubuntuInstallation of the next TensorFlow

The second chapter TensorFlow principle and core API
This chapter will focus on the tensorflow Foundation: tensorflow principle, core API and important functions. And the identification of identification code will be analyzed.
2-1 Tensorflowprinciple
2-2 TensorFlowCore API1
2-3 TensorFlowCore api2
2-4 tensorflowFoundation function 01
2-5 tensorflowFoundation function 02
2-6 tensorflowFoundation function 03
2-7 Visual learning process
2-8 Logistic regression 01
2-9 Logistic regression 02
2-10 Logistic regression 03
2-11 Loss function 01
2-12 Loss function 02
2-13 Loss function 03
2-16 Verification code recognition problem analysis
2-17 Verification code generator analysis 01
2-18 Verification code generator analysis 02

The third chapter is logistic regression model and linear regression model.
Logical regression model, learning loss function, and gradient descent method are introduced. Logical regression is used to identify verification codes.
3-1 Logistic regression model 01
3-2 Logistic regression model 02
3-3 Logistic regression model training and evaluation 01
3-4 Logistic regression model training and evaluation 02
3-5 Linear regression model 01
3-6 Linear regression model 02
3-7 Linear regression model 03
3-8 Linear regression model 04

The fourth chapter is fully connected neural network.
Introduce the full-connected neural network model, learn the ReLU function, and use the full-connected neural network to identify the validation code.
4-1 Introduction to neural network
4-2 Fully connected neural network 01
4-3 Fully connected neural network 02
4-4 ReLUExcitation function 01
4-5 ReLUExcitation function 02
4-6 Fully connected model 01
4-7 Fully connected model 02

The fifth chapter is convolution neural network.
Convolutional neural network model, learning convolution, pooling operations, learning to use dropout, using fully connected neural network for verification code recognition.
5-1 Introduction of convolution neural network 01
5-2 Introduction of convolution neural network 02
5-3 Convolution layer 01
5-4 Convolution layer 02
5-5 Convolution layer 03
5-6 Convolution layer 04
5-7 Convolution layer 05
5-8 Pool layer 01
5-9 Pool layer 02
5-10 Pool layer 03
5-11 Dropout01
5-12 Dropout02
5-13 Convolution neural network to build 01
5-14 Convolution neural network to build 02
5-15 Convolution neural network to build 03
5-16 Convolution neural network to build 04
5-17 Convolution neural network to build 05
5-18 Convolution neural network training 01
5-19 Convolution neural network training 02
5-20 Convolution neural network training 03
5-21 Convolution neural network training 04

The sixth chapter is a summary of the course.
Return to the content of the course, summarize the development process of the model, and look forward to the industry.
6-1 Course review 01
6-2 Course review 02
6-3 Course review 03
6-4 Industry outlook 01
6-5 Industry outlook 02