Developing AI with PyTorch and AWS by Daniel Whitenack

Developing AI with PyTorch and AWS

A step-by-step, practical guide to developing applications powered by ML and AI

What's included?

Video Icon 3 videos Text Icon 29 text files

Contents

Introduction to ML/AI
What is ML/AI?
Types of ML
Black Box vs. Custom ML/AI
AI building blocks
Introduction - ML/AI Building Blocks
1 min
Lesson 1 - Working with ML/AI Data - Details
Lesson 2 - Evaluation and Validation
Lesson 3 - Linear Regression and Gradient Descent
Practicum - Working with regression data
Regression
Introduction - Regression
1 min
Lesson 1 - Types of Regression
Lesson 2 - Regularization
New Tools - Jupyter, AWS SageMaker
Practicum - Training and Testing a Regression Model
Classification
Introduction - Classification
1 min
Lesson 1 - Logistic Regression - Details
Lesson 2 - kNN and Decision Trees
New Tools - ONNX
Practicum - Hyperparameters and model export
Time Series and Clustering
Lesson 1 - Time Series, ACF, PACF
Lesson 2 - Auto-regressive models
Lesson 3 - Clustering
New Tools - Prophet
Practicum - Forecasting with Prophet
Neural Networks
Lesson 1 - Neural Networks
Lesson 2 - Intro to Deep Learning
Lesson 3 - Deep Learning Example
New Tools - GPUs
Practicum - Deep Learning on a GPU
Bias, GDPR, Explanability
Lesson 1 - Bias in ML Models
Lesson 2 - GDPR, ML, and Explainability
New Tools - Industry Practices and Checklists
Practicum - Embedded project checklists

Level up your data, AI/ML, and infra skills!

Data Dan (Daniel Whitenack) is a PhD-trained data scientist with over ten years of experience developing ML/AI applications in industry. Through his courses and workshops, Dan has helped hundreds of students learn the theory and practice of machine learning, AI, data engineering, and analytics.