Jane Medium ： For a letter from an email Python Organize the table of contents in the training course , For reference in the construction of future curriculum system .

key word ： python, Artificial intelligence , Deep learning , Training courses

§01 course Program content

through I received an email about Python The curriculum of machine learning and deep learning , It is easy to design the knowledge framework of future courses .

One 、 Course content

Two 、 The handler

1、 Processing code

#!/usr/local/bin/python
# -*- coding: gbk -*-
#============================================================
# TEST1.PY -- by Dr. ZhuoQing 2021-11-01
#
# Note:
#============================================================
from head import *
strid = 2
tspcopydopstring(strid)
str= clipboard.paste().split('\r\n')
printf(" chapter | Content ")
printf("--|--")
outstr = ''
firstflag = 1
for s in str:
if s[0] in ' one two three four five six seven eight nine ten ':
if len(outstr) > 0:
printf(outstr)
outstr = s
firstflag = 1
else:
if firstflag > 0:
outstr = outstr + '|' + s
firstflag = 0
else: outstr = outstr + '<br>' + s
if len(outstr) > 0:
printf(outstr)
printf('\a')
#------------------------------------------------------------
# END OF FILE : TEST1.PY
#============================================================

2、 Form and content

 One 、 Introduction to basic learning of artificial intelligence
1. Artificial intelligence / machine learning / neural network / Overview of deep learning
2. An overview of machine learning 、 Algorithm application analysis
3. Artificial intelligence technology framework
4. Introduction to deep learning application
Two 、python Based on learning
1.print Use 2. Operators and variables
3. loop 4. List tuple Dictionary
5.if Conditions 6. function 7. modular
8. The use of the class 9.input usage
10. File read and write 11. exception handling
3、 ... and 、. Scientific computing package numpy Use learning
1.numpy Properties of 2. establish array 3.numpy Arithmetic
4.numpy The index of 5.array Merge 6.array Division
7. Random number generation and matrix operation
Four 、 Drawing Kit matplotlib Study
1. Basic usage 2.figure Images 3. Set axis
4.legend legend 5.scatter Scatter plot
5、 ... and 、python Face detection project practice
1. Use python Realize the function of face detection
6、 ... and 、 Fundamentals of artificial intelligence and machine learning
1. An overview of artificial intelligence 2. An overview of machine learning
3. Application analysis of machine learning algorithm
7、 ... and 、 Regression algorithm
1. Univariate linear regression 2. Cost function 3. Gradient descent method
4.sklearn Univariate linear regression application 5. Multiple linear regression
6.sklearn Application of multiple linear regression
Case study ： The relationship between wine quality and time
8、 ... and 、KNN Classification algorithm
1.KNN Introduction to classification algorithm
2.KNN Classification algorithm application
3.KNN Realization
Case study ： Iris classification
Nine 、 Decision tree algorithm
1. Introduction to decision tree algorithm 2. Definition of entropy
3. Decision tree algorithm and application implementation
Case study ： Prediction of user purchase behavior
Ten 、 Support vector machine
1. When is the optimal classification surface
2.SVM What is the essence of algorithm
3. How to deal with support vector machine when it is linear and inseparable
Case study ：SVM Complete the face recognition application
11、 ... and 、K-means clustering algorithm
1.K-means Algorithm is introduced
2.K-means Algorithm application
3.K-means Practical application cases of the algorithm
Case study ：NBA Cluster analysis of team strength
Twelve 、 Integrated algorithm and random forest
1.Bagging Algorithm is introduced 2. Stochastic Forest modeling method
3.Adaboost Algorithm is introduced 4.Stacking Algorithm is introduced
5.Voting Algorithm is introduced
13、 ... and 、 User default forecast - Application cases of feature engineering
1. Fill in the missing value 2. Unique value processing
3. Filter unwanted features 4. Handle multivalued ordered features
5. Handle multivalued unordered features 6. Feature data scaling
7.PCA Weft insertion 8. Data equalization
9. Model training and evaluation
fourteen 、 Fundamentals of deep learning - Introduction to neural networks
1. History of artificial neural networks
2. Single layer perceptron
3. Activation function , Loss function and gradient descent method
4.BP Algorithm is introduced
Case study ：BP The algorithm solves the problem of handwritten numeral recognition
15、 ... and 、Tensorflow Introduce
1.Tensorflow install
2.Tensorlfow Basic knowledge of
3.Tensorflow Linear regression
4.Tensorflow Nonlinear regression
5.Mnist Data set Softmax Explain
6. Use BP Neural network construction handwritten numeral recognition
7. Cross entropy (cross-entropy) Explain and use
8. Over fitting , Regularization ,Dropout
9. Various optimizers Optimizer
sixteen 、Pytorch Introduce
1.Pytorch Installation and Application
2. Build the network and complete the linear regression application
3. Build a network to complete the application of nonlinear regression
4. Complete handwritten numeral recognition
seventeen 、 Convolutional neural networks CNN application
1.CNN Convolutional neural networks
2.CNN Handwritten numeral case
3. Convolution layer 、 Pooling layer （ Mean pooling 、 Maximum pooling ）
eighteen 、 Long and short term memory network LSTM application
1.RNN Cyclic neural network
2. Long and short term memory network LSTM
3.LSTM The application case
nineteen 、 Use the pre training module Inception-v3 Type for
Image recognition
1.Inception-v3 Model explanation
2. Use the trained model for image recognition
twenty 、 Image recognition model VGG16 Project practice （ God
Classification of gas phenomena , Scene classification ）
1. VGG16 Model explanation
2. Data increase
3. Use transfer learning to complete weather phenomenon classification
4. Use migration learning to complete scene classification
The 21st 、 Actual combat of natural language processing project
1. Introduction to natural language processing project
2.word2vec Introduce
2. use LSTM Train a new text classification model
Twenty-two 、 Introduction to target detection algorithm
1. Introduction to target detection items
2. R-CNN The model,
3. SPPNET The model,
4. Fast-RCNN The model,
5. Faster-RCNN The model,
23 、 Use target detection algorithm to complete gesture recognition
1. Data preparation and annotation methods
2.Detecting Module introduction
3. Gesture recognition model training
4. Gesture recognition model application
Twenty-four 、 Optical character recognition OCR Algorithm practice
1. Use OCR The model accurately recognizes Chinese and English characters in the picture , And extract
come out
twenty-five 、 Face recognition
1. Face detection practice
2. Face key point extraction practice
3. Face recognition
hexacosa- 、 Question answering and learning platform
1、 After class projects 、 Answer questions , Learning material sharing , One on one ;
2、 establish QQ Group 、 Wechat group （ After class, it is convenient to help everyone learn ）;
3、 Free technical guidance after training , Follow up training is free ;
4、 Guide students to solve problems one-on-one according to what they are interested in and want to learn , Line
The effect is the same on and off the line , The teacher will solve your problem one-on-one remotely
5、 Provide information and python The textbook is easy to improve after class
6、 Provide the latest python Setup and remote installation services

§02 primary File forms

● python Artificial intelligence Deep learning Training courses

Two 、MATLAB Data analysis 、 machine learning