Computer Engineering is coming soon

We're still writing and reviewing the notes for every subject, and we'll open it when every subject is ready. Meanwhile you can practise aptitude, ask Aria about any subject, or see the branches that are ready.

Computer Engineering

Deep Learning

Deep feed-forward networks, CNNs, RNNs and LSTMs, GANs, deep reinforcement learning.

Interview questions
Notes for Deep Learning are being written and reviewed. Until they're up, Aria teaches every topic — ask for any part of the syllabus, with worked numericals.

Coming next in Deep Learning

  1. Deep learning vs machine learning· notes coming
  2. History, advantages and challenges of deep learning· notes coming
  3. Representation learning and deep architectures· notes coming
  4. Deep learning frameworks: TensorFlow, Keras and PyTorch· notes coming
  5. Perceptron and feed-forward networks· notes coming
  6. Forward and backpropagation· notes coming
  7. Activation functions in deep networks· notes coming
  8. Loss functions· notes coming
  9. Hyperparameters: learning rate, momentum and regularisation· notes coming
  10. Gradient descent and vanishing and exploding gradients· notes coming
  11. CNN architecture· notes coming
  12. Convolution, padding and strides· notes coming
  13. Pooling and fully connected layers· notes coming
  14. Training a CNN· notes coming
  15. Recurrent neural networks· notes coming
  16. Bidirectional and deep RNNs· notes coming
  17. Encoder–decoder sequence-to-sequence models· notes coming
  18. Long-term dependencies, LSTM and GRU· notes coming
  19. Recursive networks and echo state networks· notes coming
  20. Practical methodology: metrics, baselines and hyperparameters· notes coming
  21. Deep generative models· notes coming
  22. Boltzmann machines and deep belief networks· notes coming
  23. Generative adversarial networks· notes coming
  24. Types and applications of GANs· notes coming
  25. Deep reinforcement learning and MDPs· notes coming
  26. Dynamic programming for reinforcement learning· notes coming
  27. Q-learning and deep Q-networks· notes coming
  28. Optimisers: momentum, Nesterov, AdaGrad, RMSProp and Adam· notes coming
  29. Regularisation: dropout, batch normalisation and early stopping· notes coming
  30. Autoencoders· notes coming
  31. Denoising, sparse and contractive autoencoders· notes coming
  32. LeNet and AlexNet· notes coming
  33. Backpropagation through time· notes coming
  34. CNN architectures: VGG, GoogLeNet, ResNet and DenseNet· notes coming
  35. Object detection and image segmentation· notes coming
  36. Variational autoencoders· notes coming
  37. Transfer learning and data augmentation· notes coming
  38. Explainable and responsible AI· notes coming
  39. MLOps and model deployment· notes coming
  40. McCulloch–Pitts neuron and thresholding logic· notes coming
  41. PCA and singular value decomposition· notes coming
  42. Weight initialisation and greedy layer-wise pre-training· notes coming
  43. Learning word representations· notes coming
  44. Attention mechanism· notes coming
  45. Evolution of generative AI· notes coming
  46. Autoregressive models: RNN- and CNN-based· notes coming
  47. Scaling laws for language models· notes coming
  48. Structured probabilistic models: directed and undirected graphs· notes coming
  49. Partition function and d-separation· notes coming
  50. Sampling from graphical models· notes coming
  51. Applications of generative AI· notes coming
  52. Text, image, audio and video generation· notes coming
  53. Foundation models and large language models· notes coming
  54. Zero-shot, one-shot and few-shot prompting· notes coming
  55. Visualising and fooling CNNs: guided backpropagation and Deep Dream· notes coming