Machine Learning with PyTorch and Scikit-Learn

Develop machine learning and deep learning models with Python

Created by Sebastian Raschka, Vahid Mirjalili, Yuxi (Hayden) Liu

Dive into practical machine learning and deep learning using Python, with a focus on PyTorch and scikit-learn. Build real models, understand key algorithms, and explore advanced techniques like transformers and graph neural networks. Gain the confidence to create your own intelligent applications.

Packt | Feb 2022 | 774 min

Start Trial

LevelIntermediate

CategoriesData Science, Deep Learning Architectures and Frameworks, Scikit-learn, Python

1Giving Computers the Ability to Learn from Data
2Training Simple Machine Learning Algorithms for Classification
3A Tour of Machine Learning Classifiers Using Scikit-Learn
4 Building Good Training Datasets – Data Preprocessing
5Compressing Data via Dimensionality Reduction
6Learning Best Practices for Model Evaluation and Hyperparameter Tuning
7Combining Different Models for Ensemble Learning
8Applying Machine Learning to Sentiment Analysis
9Predicting Continuous Target Variables with Regression Analysis
10Working with Unlabeled Data – Clustering Analysis
11Implementing a Multilayer Artificial Neural Network from Scratch
12Parallelizing Neural Network Training with PyTorch
13 Going Deeper – The Mechanics of PyTorch
14Classifying Images with Deep Convolutional Neural Networks
15Modeling Sequential Data Using Recurrent Neural Networks
16Transformers – Improving Natural Language Processing with Attention Mechanisms
17Generative Adversarial Networks for Synthesizing New Data
18Graph Neural Networks for Capturing Dependencies in Graph Structured Data
19Reinforcement Learning for Decision Making in Complex Environments

What You Will Learn

You will start by exploring core machine learning concepts and gradually move to hands-on projects using PyTorch and scikit-learn. Through real-world examples and clear explanations, you will learn how to design, train, and evaluate models for a range of data types and tasks. Advanced topics like transformers and graph neural networks are introduced with practical guidance.

Key Features

Build and train neural networks, transformers, and boosting algorithms
Apply machine learning to images, text, and social media data
Master model evaluation, tuning, and best practices for real-world projects

Target Audience

Ideal for developers and data scientists with a solid understanding of Python and basic math concepts like calculus and linear algebra. If you want to move beyond the basics and apply machine learning and deep learning to real problems, this course will help you gain the skills and confidence to do so.

Related courses

Pro

Cover image for Modern Deep Learning Foundations

Cover image for AI & Python Development Megaclass

Cover image for AI Engineer Associate Course

Cover image for AI Engineering Masterclass: From Zero to AI Hero

Pro

Cover image for Python Machine Learning By Example