/Deep-Learning-Specialization-Coursera

Deep Learning Specialization Course by Coursera. Neural Networks, Deep Learning, Hyper Tuning, Regularization, Optimization, Data Processing, Convolutional NN, Sequence Models are including this Course.

Primary LanguageJupyter Notebook

Deep Learning

deeplearning.ai

N.B.: Please don't use the assignment and quiz solution at first time, only use when you get stuck really bad situation. Try to solve the problem by yourself.

About this Specialization

If you want to break into AI, this Specialization will help you do so. Deep Learning is one of the most highly sought after skills in tech. We will help you become good at Deep Learning.

In five courses, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach. - Source

Resources

  • Google Brain Residency

Course - 1

Neural Networks and Deep Learning - Coursera - GitHub - Certificate

Table of Contents

  • Week 1
    • Lesson Topic: About Neural Network(NN), Supervised Learning, Deep Learning
    • Quiz: Deep Learning
  • Week 2
    • Lesson Topic: Binary Classification, Logistic Regression, Cost Function for Logistic Regression, Gradient Descent, Derivatives, Computation Graph, Logistic Regression Gradient Descent, Python, Python - Vectorization, Vectorization Logistic Regression, Python - Broadcasting
    • Quiz: Neural Network Basics
    • Assignment: Python Basics, Logistic Regression with Neural Network mindset
  • Week 3
    • Lesson Topic: NN Representation, Computing a NN's output, Vectorized Implementation, Activation Functions, Derivatives of Activation Functions, Gradient Descent for NN, Backpropagation, Random Initialization
    • Quiz: Shallow Neural Networks
    • Assignment: Planar data classification with a hidden layer
  • Week 4
    • Lesson Topic: Deep Layer NN, Forward Propagation, Matrix, Building Block of DNN, Parameters vs Hyperparameters
    • Quiz: Key concepts on Deep Neural Networks
    • Assignment: Building your Deep Neural Network, Deep Neural Network - Application

Course - 2

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - Coursera - GitHub - Certificate

Table of Contents

  • Week 1
    • Lesson Topic: Train-Dev-Test sets, Bias and Variance, Regularization, Dropout, Other Regularization Methods, Normalizing Inputs, Vanishing and Exploding Gradients, Weight Initialization, Gradient Checking and Implementation
    • Quiz: Practical aspects of deep learning
    • Assignment: Initialization, Regularization, Gradient Checking
  • Week 2
    • Lesson Topic: Mini-batch Gradient Descent, Exponentially Weighted Averages, Bias Correction, Gradient Descent with Momentum, RMSprop, Adam Optimization, Learning Rate Decay, Problem of Local Optima
    • Quiz: Optimization Algorithms
    • Assignment: Optimization
  • Week 3
    • Lesson Topic: Tuning Process, Hyperparameters Tuning, Normalizing activations, Fitting Batch Norm, Softmax Regression, DL Frameworks, TensorFlow
    • Quiz: Hyperparameter tuning, Batch Normalization, Programming Frameworks
    • Assignment: TensorFlow

Course - 3

Structuring Machine Learning Projects - Coursera - GitHub - Certificate

Table of Contents

  • Week 1
    • Lesson Topic: ML Strategy, Orthogonalization, Single Number Evaluation Metric, Satisficing and Optimizing Metric, Train-Dev-Test Distributions, Avoidable Bias, Human Level Performance
    • Quiz: Bird recognition in the city of Peacetopia (case study)
  • Week 2
    • Lesson Topic: Error Analysis, Mismatched Training-Dev-Test Set, Transfer Learning, Multi-task Learning, End-to-End Deep Learning
    • Quiz: Autonomous driving (case study)

Course - 4

Convolutional Neural Networks - Coursera - GitHub - Certificate

Table of Contents

  • Week 1
    • Lesson Topic: Computer Vision, Edge Detection, Padding, Strided Convolutions, Convolutions Over Volume, One Layer of a CNN, Pooling Layers, CNN Example
    • Quiz: The basics of ConvNets
    • Assignment: Convolutional Model: step by step, Convolutional model: application
  • Week 2
    • Lesson Topic: Classic Networks, ResNets, 1x1 Convolution, Inception Network, Using Open Source Implementation, Transfer Learning, Data Augmentation
    • Quiz: Deep convolutional models
    • Assignment: Residual Networks
    • Optional: Keras Tutorial - The Happy House
  • Week 3
    • Lesson Topic: Object Localization, Landmark Detection, Object Detection, Bounding Box Predictions, Intersection Over Union, Non-max Suppression, Anchor Boxes, YOLO Algorithm
    • Quiz: Detection algorithms
    • Assignment: Car detection with YOLO
  • Week 4
    • Lesson Topic: Face Recognition, One Shot Learning, Siamese Network, Triplet Loss, Face Verification, Neural Style Transfer, Deep ConvNets Learning, Cost Function, Style Cost Function, 1D and 3D Generalizations
    • Quiz: Special applications: Face recognition & Neural style transfer
    • Assignment: Art generation with Neural Style Transfer, Face Recognition for the Happy House

Course - 5

Sequence Models - Coursera - GitHub - Certificate

Table of Contents

  • Week 1
    • Lesson Topic: Sequence Models, Notation, Recurrent Neural Network Model, Backpropagation through Time, Types of RNNs, Language Model, Sequence Generation, Sampling Novel Sequences, Gated Recurrent Unit (GRU), Long Short Term Memory (LSTM), Bidirectional RNN, Deep RNNs
    • Quiz: Recurrent Neural Networks
    • Assignment: Building a recurrent neural network - step by step, Dinosaur Island - Character-Level Language Modeling, Jazz improvisation with LSTM
  • Week 2
    • Lesson Topic: Word Embeddings, Embedding Matrix, Word2Vec, Negative Sampling, GloVe Word Vectors, Sentiment Classification, Debiasing Word Embeddings
    • Quiz: Natural Language Processing & Word Embeddings
    • Assignment: Operations on word vectors - Debiasing, Emojify
  • Week 3
    • Lesson Topic: Various Sequence to Sequence Architectures, Basic Models, Beam Search, Refinements to Beam Search, Error Analysis in Beam Search, Bleu Score, Attention Model Intution, Spech Recognition, Trigger Word Detection
    • Quiz: Sequence models & Attention mechanism
    • Assignment: Neural Machine Translation with Attention, Trigger word detection