Artificial Intelligence & Data Science 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.

Artificial Intelligence & Data Science

Deep Learning

Perceptrons and MLPs, training and optimisers, CNNs, RNNs and LSTMs, GANs and autoencoders, deployment.

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. Biological and artificial neurons· notes coming
  2. Feed-forward network architectures· notes coming
  3. Perceptron learning rule· notes coming
  4. Multilayer perceptron· notes coming
  5. Activation functions· notes coming
  6. Loss functions· notes coming
  7. Backpropagation· notes coming
  8. Gradient descent variants· notes coming
  9. Optimisers: AdaGrad, RMSProp and Adam· notes coming
  10. Vanishing and exploding gradients· notes coming
  11. Regularisation and dropout· notes coming
  12. Convolution and feature maps· notes coming
  13. Padding, stride and pooling· notes coming
  14. CNN architectures: LeNet to ResNet· notes coming
  15. Transfer learning· notes coming
  16. Object detection with YOLO· notes coming
  17. Recurrent neural networks· notes coming
  18. LSTM· notes coming
  19. GRU· notes coming
  20. Word embeddings: Word2Vec and GloVe· notes coming
  21. Generative adversarial networks· notes coming
  22. Autoencoders and VAEs· notes coming
  23. Model compression and pruning· notes coming
  24. Deploying deep learning models· notes coming
  25. Hyperparameters in deep learning· notes coming
  26. Training a CNN· notes coming
  27. Bidirectional and deep RNNs· notes coming
  28. Encoder-decoder sequence models· notes coming
  29. Echo state networks· notes coming
  30. Boltzmann machines and deep belief networks· notes coming
  31. Types of GANs· notes coming
  32. Deep reinforcement learning· notes coming
  33. Deep Q-networks· notes coming
  34. Image captioning and video to text· notes coming
  35. Data augmentation· notes coming
  36. Explainable and responsible AI· notes coming
  37. MLOps and model monitoring· notes coming
  38. AI agents and tool use· notes coming
  39. Deep learning frameworks: TensorFlow, Keras and PyTorch· notes coming
  40. McCulloch–Pitts neuron and thresholding logic· notes coming
  41. Momentum and Nesterov accelerated gradient descent· notes coming
  42. Eigen-decomposition, PCA and SVD· notes coming
  43. Autoencoders and their relation to PCA· notes coming
  44. Denoising, sparse and contractive autoencoders· notes coming
  45. Early stopping, parameter sharing and ensembles· notes coming
  46. Visualising CNNs: guided backpropagation and Deep Dream· notes coming
  47. Backpropagation through time· notes coming
  48. Attention mechanism· notes coming
  49. Weight initialisation: Xavier and He· notes coming
  50. Debugging strategies for deep networks· notes coming
  51. Representation learning· notes coming
  52. Optical character recognition with deep CNNs· notes coming
  53. Limitations of deep learning· notes coming
  54. Visual question answering· notes coming
  55. Keras functional API, callbacks and TensorBoard· notes coming