Explores the evolution of CNNs in image processing, covering classical and deep neural networks, training algorithms, backpropagation, non-linear steps, loss functions, and software frameworks.
Explores neural networks' ability to learn features and make linear predictions, emphasizing the importance of data quantity for effective performance.
Covers the foundational concepts of deep learning and the Transformer architecture, focusing on neural networks, attention mechanisms, and their applications in sequence modeling tasks.
Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.
Introduces a project-based course in communications and robotics, emphasizing practical projects and independent learning to prepare students for real-world challenges.
Presents an all-analog photoelectronic chip for high-speed vision tasks, addressing challenges in classical computation and proposing a hybrid optical-electrical framework.
Introduces kernel methods like SVM and regression, covering concepts such as margin, support vector machine, curse of dimensionality, and Gaussian process regression.
