Machine Learning

Machine Learning

 

Course Description:  

Machine learning is a subfield of artificial intelligence that focuses on algorithms that learn from experience. Such algorithms are the underpinning for many AI systems, particularly those used in robotics. This course highlights some of the main algorithms and approaches used in machine learning, providing both theoretical understanding as well as classroom practice of the design and implementation of machine learning algorithms.

 

Course length: 5 Days

 

Course Design:

This 5 day instructor-led classroom course combines short lectures and classroom exercises to help students develop the knowledge and skills to utilize machine learning in the growing AI industry.

 

Instructor:

Dr. Alexander Stimpson

 

Target Audience:

Tech employees, consultants, engineers, IT personnel

 

Prerequisites:

Basic programming ability in Python

Introduction to Artificial Intelligence (AI) course

 

Objectives:

Upon completion of the course, students should be able to:

  • Identify commonly used machine learning algorithms
  • Understand the theoretical basis for machine learning approaches
  • Craft simple machine learning algorithms on simple feature sets
  • Understand the strengths and limitations of different machine learning approaches

 

Course Outline:

 

Day 1:

  • Course Introduction
  • Introduction to machine learning
  • Origins of machine learning
    • Perceptron
    • Naïve Bayes
    • K-Means
    • Nearest Neighbor estimators
  • Exercise: K-Means example

 

Day 2:

  • Supervised Learning Introduction
  • Decision Trees
  • Ensembles: Bagging and Boosting
  • Exercise: AdaBoost example

 

Day 3:

  • Support Vector Machines (SVMs)
    • Maximum margin classification
    • Loss functions
    • Kernel trick
  • Reinforcement Learning
  • Exercise: SVM example

 

Day 4:

  • Artificial Neural Networks (ANNs)
    • Definitions and geometry
    • Backpropagation
  • Deep Learning
    • Autoencoders
    • Convolutional Neural Networks (CNNs)
    • Recurrent Neural Networks (RNNs)
  • Exercise: ANN example

 

Day 5:

  • Unsupervised Learning
    • Clustering
      • Centroid clustering
      • Hierarchical clustering
    • Dimensionality Reduction
      • Principal Components Analysis
    • Challenges in ML
      • Overfitting – Bias-Variance Tradeoff
      • Dimensionality
      • Redundancy/Multicollinearity
      • Noise
    • Course Summary

 

For more information: call us @ 1-(866)-477-2261 (Toll Free)