Featured resource
2026 Tech Forecast
2026 Tech Forecast

1,500+ tech insiders, business leaders, and Pluralsight Authors share their predictions on what’s shifting fastest and how to stay ahead.

Download the forecast

PyTorch

Course Summary

The PyTorch training course is designed to demonstrate the basics of data science and machine learning.

The course begins with a review of the key mathematical concepts used by the hands-on data science and machine learning labs in this course. Next, it examines Jupyter Notebooks to implement low level PyTorch code for commonly used tensor operations such as stacking, slicing, reshaping, and squeezing. The course concludes with best practices and a case study for how to build a mature data science and machine learning practice on a project or at an organization.

Purpose
Learn how to implement statistical and machine learning models using PyTorch and how to improve their performance based on an understanding of underlying mathematical principles
Audience
Participants who have either taken an introduction to Machine Learning course or have equivalent knowledge/experience.
Role
Data Engineer | Data Scientist | Software Developer
Skill Level
Intermediate
Style
Lecture | Hands-on Activities | Labs
Duration
3 Days
Related Technologies
Python | PyTorch | Machine Learning | Data

 

Learning Objectives
  • Gain an understanding of underlying applied math
  • Determine an operational approach
  • Perceive and identify Machine Learning

What You'll Learn:

In the PyTorch training course, you'll learn:

Getting started with PyTorch

  • PyTorch Models and Frameworks
  • Distributed Training Support
  • Core Python API

Jupyter Notebooks

Intermediate Machine Learning

  • Tensors as Data Structures
  • Machine Learning for Data Science
  • Regression vs. Classification Use Cases
  • Reproducibility in Machine Learning

Math Foundations Recap

  • MSE and Cross-Entropy Loss
  • Troubleshooting Gradient Descent
  • Choosing the Right Regularization
  • Type I and II Errors in Classification

Regression with Structured Data

  • Reproducible Datasets with Hashing
  • Regression Loss vs. Metric
  • Benchmark Loss and Metric for a Dataset

Classification with Structured Data

  • Deep Neural Network Models
  • Activation Functions

PyTorch APIs

  • Use Cases Regression and Classification
  • Processing Shared Datasets
  • Fault-Tolerant Distributed Training
  • TensorBoard for Monitoring and Analysis

Classification with Unstructured Image Data

  • Fashion-MNIST and Flowers Image Datasets
  • Cross-Entropy Loss and Precision, Recall, ROC, AUC Metrics
  • Deep Neural Networks for Image Classification
  • Convolutional Neural Networks for Image Classification
  • Convolutional and Maxpooling Layers

Training Convolutional Neural Networks

  • L1, L2, and Dropout Regularization
  • Batch Normalization
  • Data Augmentation
  • Transfer Learning

Advanced PyTorch

  • Storing / loading models
  • Debugging
  • Torch JIT
  • Hooks for forward / backward custom processing
  • PyTorch & GPU

Feature Engineering

  • Five Criteria for Effective Features
  • Case Studies and Best Practices
  • Feature Crosses, Quantization, Hot-one Encoding with PyTorch
  • Feature Pre-processing and Engineering in a Machine Learning Pipeline
  • Features for Wide-and-Deep Machine Learning Models

Model Training and Evaluation

  • Gradient Descent vs. Alternatives for Training
  • Netflix Prize Model Evaluation Case Study
  • Best Practices for Model Evaluation
“I appreciated the instructor's technique of writing live code examples rather than using fixed slide decks to present the material.”

VMware

Dive in and learn more

When transforming your workforce, it's important to have expert advice and tailored solutions. We can help. Tell us your unique needs and we'll explore ways to address them.

Let's chat

By clicking submit, you agree to our Privacy Policy and Terms of Use, and consent to receive marketing emails from Pluralsight.