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.
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
- Biological and artificial neurons· notes coming
- Feed-forward network architectures· notes coming
- Perceptron learning rule· notes coming
- Multilayer perceptron· notes coming
- Activation functions· notes coming
- Loss functions· notes coming
- Backpropagation· notes coming
- Gradient descent variants· notes coming
- Optimisers: AdaGrad, RMSProp and Adam· notes coming
- Vanishing and exploding gradients· notes coming
- Regularisation and dropout· notes coming
- Convolution and feature maps· notes coming
- Padding, stride and pooling· notes coming
- CNN architectures: LeNet to ResNet· notes coming
- Transfer learning· notes coming
- Object detection with YOLO· notes coming
- Recurrent neural networks· notes coming
- LSTM· notes coming
- GRU· notes coming
- Word embeddings: Word2Vec and GloVe· notes coming
- Generative adversarial networks· notes coming
- Autoencoders and VAEs· notes coming
- Model compression and pruning· notes coming
- Deploying deep learning models· notes coming
- Hyperparameters in deep learning· notes coming
- Training a CNN· notes coming
- Bidirectional and deep RNNs· notes coming
- Encoder-decoder sequence models· notes coming
- Echo state networks· notes coming
- Boltzmann machines and deep belief networks· notes coming
- Types of GANs· notes coming
- Deep reinforcement learning· notes coming
- Deep Q-networks· notes coming
- Image captioning and video to text· notes coming
- Data augmentation· notes coming
- Explainable and responsible AI· notes coming
- MLOps and model monitoring· notes coming
- AI agents and tool use· notes coming
- Deep learning frameworks: TensorFlow, Keras and PyTorch· notes coming
- McCulloch–Pitts neuron and thresholding logic· notes coming
- Momentum and Nesterov accelerated gradient descent· notes coming
- Eigen-decomposition, PCA and SVD· notes coming
- Autoencoders and their relation to PCA· notes coming
- Denoising, sparse and contractive autoencoders· notes coming
- Early stopping, parameter sharing and ensembles· notes coming
- Visualising CNNs: guided backpropagation and Deep Dream· notes coming
- Backpropagation through time· notes coming
- Attention mechanism· notes coming
- Weight initialisation: Xavier and He· notes coming
- Debugging strategies for deep networks· notes coming
- Representation learning· notes coming
- Optical character recognition with deep CNNs· notes coming
- Limitations of deep learning· notes coming
- Visual question answering· notes coming
- Keras functional API, callbacks and TensorBoard· notes coming