DS 201-2 - Building and Evaluating ML Models

In DS 201-2, we will learn how to build your own Machine Learning models, We will be using the popular SciKit Learn and TensorFlow libraries to show you how Data Scientists “learn” a model to a dataset and how to make predictions with those models. We will also be covering the finer points of ML Modeling, namely Data Prep, Parameter Selection, and testing Model performance.

Course Details

Dataset Prep

Working with Categorical Data

Boolean Masks

Regularization and Normalization

Learning Algorithms

Supervised Learning

Support Vector Machines (SVMs)

Decision Trees

Random Forests

Bayesian Models

Unsupervised Learning

K-Means Clustering

Reinforcement Learning

Neural Networks (Introduction)

Model-Parameter Selection

Cross-Validation

Model Evaluation

Cost Functions

Final Project:

Will encompass the entire data science project pipeline: data acquisition, data exploration, data analysis, model building, model evaluation.