Machine Learning Fundamentals: Statistics, Probability, and Bistromathematics with Advanced Workshop

Lesson: Calculus and Linear Algebra Review

• Essential Calculus
• Geometry and Trigonometry
• Derivatives and Slope
• Partial Derivatives
• Power Rule
• Gradient Descent
• Chain Rule
• Linear Algebra and Matrix Math
• Eigenvalues and Eigenvectors

Lesson: Statistics Review

• Essential Statistics
• Mean, Median, Variance, and deviation
• Normal / Gaussian Distribution
• Statistics in Machine Learning

Lesson: Probability Review

• Probability Theory
• Discrete Probability Distributions
• Continuous Probability Distributions
• Measure-Theoretic Probability Theory
• Central Limit and Normal Distribution
• Markov Chains
• Probability Density Function
• Probability in Machine Learning

Session: Machine Learning and Algorithms

• Sesson: Big Data and NoSQL
• The Big Data Era and the Internet of Things
• NoSQL Data Systems
• Data Transformation Pipelines

Lesson: Supervised Learning

• Supervised Learning Explained
• Classification vs. Regression
• Examples of Supervised Learning
• Key supervised algorithms (overview)

Lesson: Unsupervised Learning

• Unsupervised Learning
• Clustering
• Examples of Unsupervised Learning
• Key unsupervised algorithms (overview)

Lesson: Regression Algorithms

• Linear Regression
• Logistic Regression
• Generalized Linear Modeling
• Support Vector Regression
• Decision Trees
• Random Forests

Lesson: Classification Algorithms

• Bayes Theorem and the Naïve Bayes classifier
• Support Vector Machines
• Discriminant Analysis
• k-Nearest Neighbor (KNN)

Lesson: Clustering Algorithms

• k-Means Clustering
• Fuzzy Clustering
• Gaussian Mixture Models

Lesson: Neural Networks

• Neural Network Basics
• Hidden Markov Models (HMM)
• Recurrent Neural Networks (RNN)
• Long-Short Term Memory Networks (LSTM)

Lesson: Dimensionality Reduction

• Dimensionality Reduction Goals and Techniques
• Recap: Eigenvalues and Eigenvectors
• Single-Value Decomposition (SVD)
• Principle Component Analysis (PCA)
• Linear Discriminant Analysis (LCA)
• Generalized Discriminant Analysis (GDA)

Session: Best Practices and the Real World

• Lesson: Choosing Algorithms
• Choosing between Supervised and Unsupervised algorithms
• Choosing between Classification Algorithms
• Choosing between Regressions
• Choosing Neural Networks
• Choosing Activation Functions

Lesson: Ensemble Methods

• Ensemble Theory and Methods
• Ensemble Classifiers
• Bucket of Models
• Boosting
• Stacking

Lesson: In the Real World

• Machine Learning in Python: NumPy, Pandas, SciKit-ML, and MatPlotLIb; NLTK, Keras
• Machine Learning in R
• Machine Learning in Java
• Machine Learning with Apache Madlib
• Hadoop, MapReduce, and Mahout
• Spark and MLLib
• TensorFlow

Skill-focused, Hands- on Learning:  This class is “technology-centric”, designed to train attendees in essential skills, coupling the most current, effective techniques with the soundest industry practices. This course is about 50% hands-on lab and 50% lecture, with extensive programming exercises designed to reinforce fundamental skills and concepts learned in the lessons.  Our courses include a wide range of complementary materials and labs to ensure all students are appropriately challenged or assisted at all times, no matter their incoming skill level.

This 5-day course has the students creating ground-up implementations of key mathematics and algorithms using Python, NumPy, and basic libraries for building a deeper mathematics-programming intuition.