Prerequisites

• knowledge of basic computer science principles and skills
• Familiarity with the basic probability theory.
• Familiarity with the basic linear algebra

Timing

• 6 weeks : Python + linear algebra
• 6 weeks: machine learning
• 6 weeks: deeplearning

Theory content

• Introduction
• Linear Algebra Review
• Python
• Linear Regression with Multiple Variables
• Logistic Regression
• Neural Networks: Representation
• Neural Networks: Learning
• Advice for Applying Machine Learning
• Support Vector Machines
• Unsupervised Learning
• Anomaly Detection
• Large Scale Machine Learning
• Applications
• Algorithmic models of learning.
• Learning classifiers, functions, relations, grammars.
• decision trees
• support vector machines
• Bayesian networks
• bag of words classifiers
• N-gram models
• Markov and Hidden Markov models
• probabilistic relational models
• association rules,
• feature selection and visualization.
• k-means clustering
• Reinforcement learning
• Learning from heterogeneous, distributed data
• applications in data mining,
• pattern recognition.
• Deeplearning
• Neural Networks and Deep Learning
• Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
• Structuring Machine Learning Projects
• Convolutional Neural Networks
• Sequence Models

practical : Programming Assignment

• Octave/Matlab Tutorial
• Python Basics with numpy
• Logistic Regression with a Neural Network mindset
• Linear Regression with One Variable
• Regularization
• Neural Networks: Representation
• Neural Networks: Learning
• Advice for Applying Machine Learning
• Machine Learning System Design
• Support Vector Machines
• Unsupervised Learning
• Principal Component Analysis
• Anomaly Detection
• Recommender Systems
• Large Scale Machine Learning
• Photo OCR
• Planar data classification with a hidden layer
• Building your deep neural network: Step by Step
• Deep Neural Network Application
• Regularization
• Gradient Checking
• Optimization algorithms
• Tensorflow
• Bird recognition in the city of Peacetopia (case study)
• Autonomous driving (case study)
• Convolutional Model: step by step
• Convolutional model: application
• Keras Tutorial – The Happy House
• Residual Networks
• Car detection with YOLOv2
• Special applications: Face recognition & Neural style transfer
• Art generation with Neural Style Transfer
• Dinosaur Island – Character-Level Language Modeling
• Operations on word vectors – Debiasing
• Neural Machine Translation with Attention
• Trigger word detection