Neural Network Deep Learning

This course aims to provide students with a comprehensive foundation in neural networks and deep learning, covering the underlying principles, model architectures, learning algorithms, and practical considerations involved in designing and training deep neural networks. Students will learn both classical and modern deep learning models, including feedforward networks, convolutional neural networks, recurrent neural networks, Transformers, autoencoders, generative adversarial networks, and diffusion models. The course also introduces key concepts in model selection, generalization, representation learning, sequence modeling, attention mechanisms, and modern generative AI, preparing students to understand, implement, and apply deep learning methods to problems in artifi cial intelligence and data science.