Applied Machine Learning: Algorithms (2019)

Course details

In the first installment of the Applied Machine Learning series, instructor Derek Jedamski covered foundational concepts, providing you with a general recipe to follow to attack any machine learning problem in a pragmatic, thorough manner. In this course—the second and final installment in the series—Derek builds on top of that architecture by exploring a variety of algorithms, from logistic regression to gradient boosting, and showing how to set a structure that guides you through picking the best one for the problem at hand. Each algorithm has its pros and cons, making each one the preferred choice for certain types of problems. Understanding what actually drives each algorithm, as well as their benefits and drawbacks, can give you a significant competitive advantage as a data scientist.

Learning objectives
Models vs. algorithms
Cleaning continuous and categorical variables
Tuning hyperparameters
Pros and cons of logistic regression
Fitting a support vector machines model
When to consider using a multilayer perceptron model
Using the random forest algorithm
Fitting a basic boosting model

Concepts

Introduction

The power of algorithms in machine learning
What you should know
What tools you need
Using the exercise files

Review of Foundations

Defining model vs. algorithm
Process overview
Clean continuous variables
Clean categorical variables
Split into train, validation, and test set

Logistic Regression

What is logistic regression
When should you consider using logistic regression
What are the key hyperparameters to consider
Fit a basic logistic regression model

Support Vector Machines

What is Support Vector Machine
When should you consider using SVM
What are the key hyperparameters to consider
Fit a basic SVM model

Multi-layer Perceptron

What is a multi-layer perceptron
When should you consider using a multi-layer perceptron
What are the key hyperparameters to consider
Fit a basic multi-layer perceptron model

Random Forest

What is Random Forest
When should you consider using Random Forest
What are the key hyperparameters to consider
Fit a basic Random Forest model

Boosting

What is boosting
When should you consider using boosting
What are the key hyperparameters to consider boosting
Fit a basic boosting model

Summary

Why do you need to consider so many different models
Conceptual comparison of algorithms
Final model selection and evaluation

Conclusion

Next steps