Deep learning Diploma

Course details

• Algorithms 1
• Algorithms 2
• Calculus 1
• Stochastic gradient descent
• Backpropagation
• Neural Networks Part 1: Setting up the Architecture 
• model of a biological neuron
• activation functions
• neural net architecture
• representational power
• Neural Networks Part 2: Setting up the Data and the Loss
• Preprocessing
• Weight initialization
• Batch normalization
• Regularization (L2/dropout)
• Loss functions
• Neural Networks Part 3: Learning and Evaluation 
• Gradient checks
• Momentum
• Adagrad/RMSprop
• hyperparameter optimization
• model ensembles
• Deep Learning for Computer Vision   
• Images processing 1
• Image processing 2
• Convolutional Neural Networks
• layers, spatial arrangement, layer patterns, layer sizing patterns
• AlexNet/ZFNet/VGGNet case studies
• computational considerations
• Understanding and Visualizing Convolutional Neural Networks
• tSNE embeddings
• Deconvnets
• data gradients
• fooling ConvNets
• human comparisons
• Transfer Learning and Fine-tuning Convolutional Neural Networks
• Object detection
• Intro to semantic segmentation, instance segmentation
• U-net architecture
• Post processing
• Deep Learning for NLP (intro)
• Regular expressions & word tokenization
• Simple topic identification
• Named-entity recognition
• Project