The "Big Data Machine Learning" course is a basic theoretical course for senior undergraduates or graduate students in the information discipline. The purpose is to cultivate students to have an in-depth understanding of the theoretical basis of big data machine learning, a firm grasp of big data machine learning methods, and the ability to solve practical problems. and other comprehensive abilities. The main contents of the course include: basic theories of statistical learning, basic methods of machine learning, and deep learning theories and methods.
Total of 113 lessons15 hours and 39 minutes and 33 seconds
In terms of its academic connotation, pattern recognition is a subject of data processing and information analysis. In terms of its application characteristics, it belongs to the categories of artificial intelligence and machine learning. The pattern recognition course is a professional basic course for undergraduates in information engineering and related majors. It is also an elective course for many other majors and occupies a very important position in the knowledge structure. It is of great significance for consolidating learned knowledge, carrying out professional course study and future work.
Total of 35 lessons22 hours and 6 minutes and 8 seconds
(01) Preliminary machine learning and related mathematics (02) Mathematical statistics and parameter estimation (03) Matrix analysis and application (04) Preliminary convex optimization (05) Regression analysis and engineering application (06) Feature engineering (07) Workflow and model Tuning (08) Maximum entropy model and EM algorithm (09) Recommended system and application (10) Clustering algorithm and application (11) Decision tree random forest and adaboost (12) SVM (13) Bayesian method (14) Topic Model (15) Bayesian inference sampling and variation (16) Artificial neural network (17) Convolutional neural network (18) Recurrent neural network and LSTM (19) Caffe&Tensor Flow&MxNet Introduction (20) Bayesian network and HMM (extra Supplement) word embedding word embedding
Total of 21 lessons1 days and 22 hours and 12 minutes and 36 seconds
Main content: definition of artificial intelligence, tree search algorithm, information-free search strategy, heuristic search strategy, constraint satisfaction problem solving, game algorithm, Bayesian network, hidden Markov model, Kalman filter. Features: The teaching time of artificial intelligence courses in the school is 32 hours. It is a required professional course for master's students in computer science and technology. Since the basic theory of artificial intelligence involves intelligent search, reasoning, machine learning, etc., it is an essential theoretical foundation for various research directions of current information graduate students, and can lay a good foundation for students to conduct in-depth research in various directions. The ideas can be applied to pattern recognition, intelligent analysis and processing of images and videos, data mining and intelligent processing applications of various information. Since the course teaching focuses on the description of algorithms, students will not find it boring and can master intelligent ideas well through practical exercises combined with programming.
Total of 40 lessons8 hours and 47 minutes and 20 seconds
EEWorld
subscription
account
EEWorld
service
account
Automotive
development
circle
About Us Customer Service Contact Information Datasheet Sitemap LatestNews
Room 1530, 15th Floor, Building B,
No.18 Zhongguancun Street,
Haidian District,
Beijing, Postal Code: 100190
China
Telephone: 008610 8235 0740
京公网安备 11010802033920号
