Python for Machine Learning

Module 1: Environment Setup

• Installing PyCharm and Python on Windows
• Installing PyCharm and Python on Mac
• Installing TensorFlow and Keras

Module 2: Artificial Intelligence Basics

• Why to learn artificial intelligence and machine learning?
• Introduction to machine learning

Module 3: Linear Regression

• Linear regression introduction
• Linear regression theory - optimization
• Linear regression theory - gradient descent
• Linear regression implementation

Module 4: Logistic Regression

• Logistic regression introduction
• Logistic regression example - sigmoid function
• Cross validation introduction
• Cross validation example

Module 5: K-Nearest Neighbor Classifier

• K-nearest neighbor introduction
• K-nearest neighbor introduction - lazy learning
• K-nearest neighbor introduction - Euclidean-distance
• K-nearest neighbor implementation 

Module 6: Naive Bayes Classifier

• Naive Bayes classifier introduction
• Naive Bayes classifier implementation
• Text clustering - basics
• Text clustering - inverse document frequency (TF-IDF)
• Naive Bayes example - clustering news

Module 7: Support Vector Machines (SVMs)

• Support vector machine introduction - linear case
• Support vector machine introduction - non-linear case
• Support vector machine introduction - kernels
• Support vector machine example - simple
• Support vector machine example - iris dataset
• Support vector machines example - parameter tuning
• Support vector machine example - digit recognition
• Support vector machine example - digit recognition

Module 8: Machine Learning Project - Face Recognition

• The Olivetti dataset
• Understanding the dataset
• Finding optimal number of principal components (eigenvectors)
• Understanding "eigenfaces"
• Constructing the machine learning models
• Using cross-validation

Module 9: Feed-Forward Neural Network Theory

• Artificial neural networks - inspiration
• Artificial neural networks - layers
• Artificial neural networks - the model
• Why to use activation functions?
• Neural networks - the big picture
• Using bias nodes in the neural network
• How to measure the error of the network?
• Optimization with gradient descent
• Gradient descent with backpropagation

Module 10: Machine Learning Project - Identifying Objects with CNNs

• What is the CIFAR-10 dataset?
• Preprocessing the data
• Fitting the model
• Tuning the parameters - regularization