Information Technology 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.
Information Technology
Deep Learning
MLPs and backpropagation, regularisation, CNNs and AlexNet, RNNs and LSTMs, autoencoders, transfer learning, applications.
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
- Multilayer perceptron and backpropagation· notes coming
- Gradient descent and optimisers· notes coming
- Vanishing gradient problem· notes coming
- Activation functions· notes coming
- Regularisation: dropout, L1 and L2· notes coming
- Convolution and parameter sharing· notes coming
- Pooling· notes coming
- CNN architecture· notes coming
- AlexNet· notes coming
- Recurrent neural networks· notes coming
- LSTM networks· notes coming
- Encoder-decoder architectures· notes coming
- Recursive neural networks· notes coming
- Undercomplete autoencoders· notes coming
- Sparse and denoising autoencoders· notes coming
- Contractive autoencoders· notes coming
- Applications of autoencoders· notes coming
- Greedy layer-wise pre-training· notes coming
- Transfer learning and domain adaptation· notes coming
- DenseNet· notes coming
- Deep learning for image classification· notes coming
- Deep learning for speech and NLP· notes coming
- Deep learning recommender systems· notes coming
- History and success stories of deep learning· notes coming
- McCulloch–Pitts neuron and perceptron learning· notes coming
- Eigendecomposition, PCA and SVD· notes coming
- Dataset augmentation, noise injection and ensembles· notes coming
- Learning word vector representations· notes coming
- CNN architectures: ZF-Net, VGGNet, GoogLeNet and ResNet· notes coming
- Visualising and fooling CNNs: guided backpropagation and Deep Dream· notes coming
- Backpropagation through time, vanishing and exploding gradients· notes coming
- Attention mechanism· notes coming
- Weight initialisation: Xavier and He· notes coming