Welcome to the repository for my submissions, notes, and related code for the specialization. The specialization consists of five courses. Completion certificate can be viewed here.

Certificate: here.

Programming assignments

• Week 1 (No programming assignments)
• Week 2 - PA 1 - Python Basics with Numpy
• Week 2 - PA 2 - Logistic Regression with a Neural Network mindset
• Week 3 - PA 3 - Planar data classification with one hidden layer
• Week 4 - PA 4 - Building your Deep Neural Network: Step by Step
• Week 4 - PA 5 - Deep Neural Network for Image Classification: Application

Topics covered

• Week 1: Introduction, NN, Why Deep learning
• Week 2: Logistic regression, Gradient Descent, Derivatives, Vectorization, Python Broadcasting
• Week 3: NN, Activation function, Backpropagation, Random Initialization
• Week 4: Deep L-layer Neural network, Matrix dimension verfication, Why Deep representation, Building blocks of NN, Parameters vs Hyperparameters, Relationship with brain

Certificate: here.

Programming assignments

• Week 1 - PA 1 - Initialization
• Week 1 - PA 2 - Regularization
• Week 1 - PA 3 - Gradient Checking
• Week 2 - PA 4 - Optimization Methods
• Week 3 - PA 5 - TensorFlow Tutorial

Topics covered

• Week 1: Train/Dev/Test set, Bias/Variance, Regularization, Why regularization, Dropout, Normalizing inputs, vanishing/exploding gradients, Gradient checking
• Week 2: Mini-batch, Exponentially weighted average, GD with momentum, RMSProp, Adam optimizer, Learning rate decay, Local optima problem, Plateaus problem
• Week 3: Tuning process, Hyperparameter selection, Batch Normalization, Softmax regression, Deep learning programming framework

Certificate: here.

Programming assignments: No programming assignment.

Topics covered

• Week 1: Why ML Strategy?, Orthogonalization, Single number evaluation metric, Satisficing and optimizing metrics, Train/dev/test distribution, Human level performance, Avoidable bias
• Week 2: Error analysis, Incorrectly labeled data, Data augmentation, Transfer learning, Multitask learning, End-to-End Deep learning

Certificate: here.

Programming assignments

• Week 1 - PA 1 - Convolutional Model: step by step
• Week 1 - PA 2 - Convolutional Neural Networks: Application
• Week 2 - PA 3 - Residual Networks
• Week 2 - PA 4 - Transfer Learning with MobileNet
• Week 3 - PA 5 - Car detection with YOLO for Autonomous Driving
• Week 3 - PA 6 - Image Segmentation Unet
• Week 4 - PA 7 - Face Recognition
• Week 4 - PA 8 - Art Generation with Neural Style Transfer

Topics covered

• Week 1: Computer vision, Edge detection, Padding, Strided convolution, Convolutions over volume, Pooling layers, CNN, Why CNN?
• Week 2: LeNet-5, AlexNet, VGG-16, ResNets, 1x1 convolutions, InceptionNet, Data augmentation
• Week 3: Object localization, Landmark detection, Object detection, Sliding window, Bounding box prediction, Intersection over union(IOU), Non-max suppression, Anchor box, YOLO algorithm
• Week 4: Face recognition, One-shot learning, Siamese network, Neural style transfer

Certificate: here.

Programming assignments

• Week 1 - PA 1 - Building a Recurrent Neural Network - Step by Step
• Week 1 - PA 2 - Dinosaur Land -- Character-level Language Modeling
• Week 1 - PA 3 - Jazz improvisation with LSTM
• Week 2 - PA 4 - Word Vector Representation and Debiasing
• Week 2 - PA 5 - Emojify!
• Week 3 - PA 6 - Neural Machine Translation with Attention
• Week 3 - PA 7 - Trigger Word Detection
• Week 4 - PA 8 - Transformer Implementation
• Week 4 - PA 9 - Transformer Application: Named Entity Recognition
• Week 4 - PA 10 - Transformer Application: Question Answering
• Week 4 - PA 11 - Transformer Application: Transformer Preprocessing

Topics covered

• Week 1: RNN, Notation, BPTT, RNN-variants, Vanishing gradient, GRU, LSTM, Bidirectional RNN, Deep RNN
• Week 2: Word representation, Word embedding, Cosine similarity, Word2Vec, Negetive sampling, GloVe word vectors, Debiasing word
• Week 3: Beam search, Error analysis in Beam search, Bleu score, Attention model, Speech recognition
• Week 4: Transformer Intution, Self Attention, Multi-head Attention, Transformers