Explores neural networks' ability to learn features and make linear predictions, emphasizing the importance of data quantity for effective performance.
Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.
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.
Covers the use of transformers in robotics, focusing on embodied perception and innovative applications in humanoid locomotion and reinforcement learning.
Explores the application of machine learning in medicine, emphasizing interpretability, variability between patients, and the quest for transparent equations in medical models.
Explores the intersection between neuroscience and machine learning, discussing deep learning, reinforcement learning, memory systems, and the future of bridging machine and human-level intelligence.