This “skills-centric” course is about 50% hands-on lab and 50% lecture, with extensive practical exercises designed to reinforce fundamental skills, concepts and best practices taught throughout the course. Throughout the course students will learn about and explore popular machine learning algorithms, their applicability and limitations and practical application of these methods in a machine learning environment. 

This course reviews key foundational mathematics and introduces students to the algorithms of Data Science. Working in a hands-on learning environment, students will explore: 

• Popular machine learning algorithms, their applicability and limitations 
• Practical application of these methods in a machine learning environment 
• Practical use cases and limitations of algorithms 
• Core machine learning mathematics and statistics 
• Supervised Learning vs. Unsupervised Learning 
• Classification Algorithms  
• Regression Algorithms  
• Neural Networks 
• How to choose an algorithm for a given problem 
• How to choose parameters and activation functions 
• Ensemble methods 

Need different skills or topics? If your team requires different topics or tools, additional skills or custom approach, this course may be further adjusted to accommodate. We offer additional AI, machine learning, data science, programming, Python/R and other related topics that may be blended with this course for a track that best suits your needs.  

Students attending this course should be familiar with Enterprise IT, have a general (high-level) understanding of systems architecture, as well as some knowledge of the business drivers that might be able to take advantage of applying AI. 

This course is ideally suited for a wide variety of technical learners who need an introduction to the core skills, concepts and technologies related to AI programming and machine learning. Attendees might include: 

• Developers aspiring to be a 'Data Scientist' or Machine Learning engineers 
• Analytics Managers who are leading a team of analysts  
• Business Analysts who want to understand data science techniques 
• Information Architects who want to gain expertise in Machine Learning algorithms  
• Analytics professionals who want to work in machine learning or artificial intelligence 
• Graduates looking to build a career in Data Science and machine learning 
• Experienced professionals who would like to harness machine learning in their fields to get more insight about customers 

Please note that this list of topics is based on our standard course offering, evolved from typical industry uses and trends. We will work with you to tune this course and level of coverage to target the skills you need most. Course agenda, topics and labs are subject to adjust during live delivery in response to student skill level, interests and participation.  

Fundamental Concepts 

• What is deep learning? 
• Supervised Learning 
• Unsupervised Learning 
• Parametric / nonparametric Learning 
• Statistics and Probability Overview 

Neural Predictions (Forward Propagations) 

• Simple Neural Network Predictions 
• What is a Neural Network? 
• Make predictions with multiple inputs 
• Predict with multiple inputs and outputs 
• Predict on predictions 
• NumPy (Numerical Python Primer) 

Gradient Descent 

• Measuring Error 
• Crude Learning 
• Characteristics of crude learning 
• Calculate direction and error 
• Single iteration of gradient descent 
• Divergence 
• Alpha 
• Learning   

Neural Network Generalization 

• Gradient Descent with multiple inputs 
• Freezing weights 
• Gradient Descent with multiple outputs and inputs 
• What do weights learn 
• Linear Algebra and the Dot Product (how does it help us learn) 

Backpropagation and Building your First E2E Neural Network 

• Build a Neural Network 
• Learn the whole dataset 
• Full, Batch, Stochastic Gradient Descent 
• Overfitting 
• Correlations 
• Backpropagation 
• Putting it all together 

Machine Learning Regression 

• What is Classification 
• Binary Classification for Machine Learning 
• Multi-Class Classification 
• Multi-Label Classification for Machine Learning 
• Imbalanced Classification for Machine Learning 
• Hands-on 
• Assessment 

Machine Learning Classification  

• What is Classification 
• Binary Classification for Machine Learning 
• Multi-Class Classification 
• Multi-Label Classification for Machine Learning 
• Imbalanced Classification for Machine Learning 
• Hands-on 
• Assessment 
• Program Assessment 
• Assessment Solutions 

Machine Learning Resampling and Tuning 

• Resampling 
• Evaluation Metrics 
• Evaluation Metrics for Regression 
• Evaluation Metrics for Classification 
• Hyperparameter Tuning 
• Grid Search 
• Random Search 
• Hands-on 
• Assessment 

Ensemble Methods 

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