Introduction

Artificial Intelligence and Deep Learning focuses on the fundamental theories, key methods, and engineering practices of artificial intelligence and deep learning. It introduces the history, research areas, and typical applications of artificial intelligence and pattern recognition, while reviewing essential mathematical foundations such as probability, linear algebra, calculus, optimization, and information theory. The course covers basic concepts of machine learning, model evaluation, regularization and generalization, linear regression, logistic regression, perceptron, Softmax regression, gradient descent, and common optimization algorithms. In the deep learning part, students study feedforward neural networks, backpropagation, training optimization, regularization methods, convolutional neural networks, recurrent neural networks, attention mechanisms, Transformer models, self-supervised learning, and reinforcement learning. Practical experiments are conducted on Huawei Cloud ModelArts and MindSpore, including image classification, handwritten digit recognition, sentiment analysis, maze games, model compression, and mobile deployment, helping students develop abilities in problem analysis, algorithm design, system implementation, and performance evaluation.