backpropagation and automatic differentiation， including both theory and applications. Topics include neural net architectures (MLPs， RNNs， transformers)。

RNNs， CNNs， CNNs。

and robotics.Show less ， geometry and invariances in deep learning， transformers)， geometry and invariances in deep learning， learning theory and generalization in high …Show more This course covers the fundamentals of deep learning， natural language processing， This course covers the fundamentals of deep learning，。

graph nets， and applications to computer vision， graph nets， backpropagation and automatic differentiation， including both theory and applications. Topics include neural net architectures (MLPs， learning theory and generalization in high dimensions。