"神经网络与深度学习绪论及课程概要详解"

"Neural Networks and Deep Learning" is a course that delves into the subfield of artificial intelligence known as neural networks and deep learning. These models are built upon artificial neurons and aim to solve the problem of contribution allocation in machine learning. The course covers a wide range of topics, including linear models, basic network models, feedforward neural networks, convolutional neural networks, recurrent neural networks, network optimization and regularization, memory and attention mechanisms, unsupervised learning, advanced models such as probability graph models, Boltzmann machines, deep belief networks, deep generative models, and deep reinforcement learning. In order to fully grasp the concepts presented in the course, it is recommended that students have a solid foundation in linear algebra, calculus, mathematical optimization, probability theory, and information theory. The course also recommends several textbooks for further reading, including "Neural Networks and Deep Learning" by the course instructors, as well as "Pattern Recognition and Machine Learning" by CM Bishop and "Machine Learning" by Stephen Wright. Overall, "Neural Networks and Deep Learning" provides a comprehensive overview of these complex models and the mathematical foundations behind them. Through this course, students will gain a deep understanding of neural networks and their applications in various machine learning problems, paving the way for further exploration and research in the field of artificial intelligence.