Register Sign in
CATECP HOME

About

Lecture

Projects

Resource

News

Partner

Contact

Register Sign in
[Artificial Intelligence Technology Application] 3.Deep Learning
#ICT# #IOT#

Lesson Code: TCEN2026H041

Clicks：
LIKE
Academic Hours
2.30hours
Publish Date
Jan 2026

Lecturer

1. Lecturer QI JiamingSichuan Vocational College of Information Technology

General Introduction
This course is an introductory deep learning program designed for beginners in artificial intelligence, suitable for university students in related majors as well as general learners. Centered on TensorFlow 2.0 as the primary tool, it systematically explains fundamental deep learning theories,
mainstream models such as CNNs, and practical applications, covering the full workflow from environment setup to hands-on project development. Through 120 minutes of online instructional videos, the course helps learners acquire core deep learning skills and establishes a solid foundation for further study or project development.

This Course is for
1. Helping trainees understand the fundamental concepts of deep learning, mainstream models such as CNNs, and emerging directions such as reinforcement learning; as well as master the core operations and development workflow of the TensorFlow 2.0 framework.
2. Enabling trainees to independently complete tasks such as data preprocessing, model construction, training, and evaluation, while developing practical abilities to solve typical problems in computer vision, natural language processing, and related fields.
3. Teaching trainees to apply deep learning through hands-on practice, cultivating engineering-oriented thinking, enabling them to use learned techniques in real-world scenarios, and guiding them to understand the development trends of deep learning and large model technologies.

Learning Materials

1. Corresponding PPT
2. Online Course Video
3. Simulation Question Banks

Recognized By

Benefits of Learning

1. Being able to demonstrate foundational mathematical and programming abilities, including familiarity with linear algebra and probability and statistics, as well as experience in Python programming and the use of libraries such as NumPy and Pandas for data processing.
2. Having the capability to understand introductory machine learning concepts, including supervised learning, loss functions, and optimization algorithms, and preferably having experience with tools such as Scikit-learn.
3. Being capable of engaging in self-directed learning by using documentation and community resources to troubleshoot code and adapt effectively to online learning environments.
4. Having the ability to work with appropriate hardware, including a computer with at least 8 GB of RAM and an i5 or higher processor, with a GPU at the level of an RTX 2070 or above recommended.
5. Being able to operate essential software tools, including managing environments with Anaconda, using a Python IDE, and completing programming exercises independently.

Courses Videos
Chapter 1 Introduction to Deep Learning and TensorFlow Installation.mp4playChapter 2 Neural network foundation(1).mp4playChapter 2 Neural network foundation(2).mp4playChapter 2 Neural network foundation(3).mp4playChapter 3 TensorFlow implementation of neural networks（1）.mp4playChapter 3 TensorFlow implementation of neural networks（2）.mp4playChapter 3 TensorFlow implementation of neural networks（3）.mp4playChapter 4 Basics of convolutional neural networks（1）.mp4playChapter 4 Basics of convolutional neural networks（2）.mp4playChapter 4 Basics of convolutional neural networks（3）.mp4playChapter 5 Clacssic Convolutional Neural Networks (1).mp4playChapter 5 Clacssic Convolutional Neural Networks (2).mp4playChapter 5 Clacssic Convolutional Neural Networks (3).mp4playChapter 5 Clacssic Convolutional Neural Networks (4).mp4playChapter 5 Clacssic Convolutional Neural Networks (5).mp4play

Downloads
Please log in and download

TEL:+855 99 294 999

FAX:+855 99 294 999

E-MAIL:catecp@china-asean.cn