Training background

The wave of artificial intelligence is sweeping the world, and all kinds of training courses emerge at the historic moment, but there are few practical courses that can really allow students to systematically and fully grasp the knowledge points, and can put what they have learned into practice. This course includes important concepts and common algorithms for machine learning, deep learning (decision trees, association rules, clustering, Bayesian networks, neural networks, support vector machines, hidden Markov models, genetic algorithms, CNN, RNN, GAN, etc.), as well as current hotspots in the field of artificial intelligence.

Training object

Students in computer-related majors, or science and engineering majors, and familiar with at least one programming language;

Java development engineer, machine learning engineer, machine learning development engineer, artificial intelligence engineer, AI application engineer;

Training income

1. Master the basic knowledge of data mining and machine learning

2. Master the advanced knowledge of data mining and machine learning

3. Master the theory and practice of deep learning

4. Master Python development skills

5. Master deep learning tools: TensorFlow, Keras, etc

6. Provide targeted suggestions for students' follow-up project application

Training outline

Part 1, first machine learning
Concepts and Terms (AI, Data Mining, Machine learning)
Objects of data mining
Key techniques for data mining
The expression of knowledge
Installation of the Python's
data preprocessing
Regression and timing analysis
decision tree

The second part is a typical algorithm in machine learning
clustering
Association rules
Both Naive Bayes and KNN
V Maximum likelihood estimation together with the EM algorithm
Performance evaluation index

Part three, neural network topic
BP neural network
Simulated annealing algorithm together with other neural networks
Optimization methods in machine learning
genetic algorithm

Part four, machine learning is advanced
support vector machine
hidden Markov model
Text mining
V runs from LSA to LDA

Part five, machine learning advanced and deep learning preliminary
Using the unlabeled samples
V ensemble learning
reinforcement learning
deep learning-1

Part 6, Deep learning
optimization algorithm
Avoid getting used to
Typical application scenarios
RNN、LSTM、 GRU
GAN、DQN

  NOA|挪亚2022年课程计划.pdf