Course info

This course introduces the principles and applications of deep learning and reinforced learning. Students will learn how to design and implement deep neural networks for solving various machine learning problems, as well as how to train and optimize these networks using modern techniques such as backpropagation, stochastic gradient descent, and regularization. Through a combination of lectures, programming assignments, and a final project, students will gain practical experience in building and training deep neural networks and reinforcement learning agents.

Course Topics:

1. Introduction to deep learning and neural networks
2. Feedforward networks and backpropagation
3. Convolutional neural networks for image recognition
4. Recurrent neural networks for sequence modeling
5. Optimization techniques for deep learning
6. Introduction to reinforcement learning
7. Applications of deep learning and reinforcement learning

Course Learning Outcomes:

Upon completion of this course, students will be able to:

1. Understand the principles and applications of deep learning and reinforcement learning.
2. Regression and Logistics
3. Design and implement various types of neural networks using modern frameworks such as TensorFlow.
4. Train and optimize deep neural networks for various machine learning tasks.
5. Understand the fundamentals of reinforcement learning and build reinforcement learning agents for simple tasks.
6. Apply deep learning and reinforcement learning to solve real-world problems in areas such as computer vision, natural language processing, and robotics.