课时1：Week 1 – Lecture- History, motivation, and evolution of Deep Learning

课时2：Week 1 – Practicum- Classification, linear algebra, and visualisation

课时3：Week 2 – Lecture- Stochastic gradient descent and backpropagation

课时4：Week 2 – Practicum- Training a neural network

课时5：Week 3 – Lecture- Convolutional neural networks

课时6：Week 3 – Practicum- Natural signals properties and CNNs

课时7：Week 4 – Practicum- Listening to convolutions

课时8：Week 5 – Lecture- Optimisation

课时9：Week 5 – Practicum- 1D multi-channel convolution and autograd

课时10：Week 6 – Lecture- CNN applications, RNN, and attention

课时11：Week 6 – Practicum- RNN and LSTM architectures

课时12：Week 7 – Practicum- Under- and over-complete autoencoders

课时13：Week 7 – Lecture- Energy based models and self-supervised learning

课时14：Week 8 – Lecture- Contrastive methods and regularised latent variable models

课时15：Week 8 – Practicum- Variational autoencoders

课时16：Week 9 – Lecture- Group sparsity, world model, and generative adversarial networks (GANs)

课时17：Week 9 – Practicum- (Energy-based) Generative adversarial networks

课时18：Week 10 – Practicum- The Truck Backer-Upper

课时19：Week 10 – Lecture- Self-supervised learning (SSL) in computer vision (CV)

课时20：Week 11 – Practicum- Prediction and Policy learning Under Uncertainty (PPUU)

课时21：Week 11 – Lecture- PyTorch activation and loss functions

课时22：Week 12 – Practicum- Attention and the Transformer

课时23：Week 12 – Lecture- Deep Learning for Natural Language Processing (NLP)

课时24：Week 13 – Practicum- Graph Convolutional Neural Networks (GCN)

课时25：Week 13 – Lecture- Graph Convolutional Networks (GCNs)

课时26：Week 14 – Lecture- Structured prediction with energy based models

课时27：Week 14 – Practicum- Overfitting and regularization, and Bayesian neural nets

课时28：Week 15 – Practicum part A- Inference for latent variable energy based models (EBMs)

课时29：Week 15 – Practicum part B- Training latent variable energy based models (EBMs)

课时30：Matrix multiplication, signals, and convolutions

课时31：Supervised and self-supervised transfer learning (with PyTorch Lightning)

课时32：Four decades in Machine Learning- a Personal Journey by Yann LeCun