Time Series with PyTorch
Modern Deep Learning Toolkit for Real-World Forecasting Challenges
Created by Graeme Davidson, Lei Ma
Explore practical deep learning techniques for time series forecasting using PyTorch. Move from foundational neural network concepts to advanced architectures and real-world applications. Gain the skills to confidently tackle forecasting, classification, and anomaly detection tasks.
Packt | May 2026 | 606 min
What You Will Learn
You will start by working with PyTorch fundamentals and gradually build up to designing and training deep learning models for time series data. Through hands-on projects and real-world datasets, you will experiment with different architectures and evaluation strategies, learning how to select and tune models for specific forecasting challenges.
Key Features
- Build and train neural networks for time series forecasting using PyTorch
- Apply advanced models like transformers, N-BEATS, and Temporal Fusion Transformer
- Use transfer learning, synthetic data, and self-supervised methods for robust solutions
Target Audience
Ideal for data analysts, scientists, and students with basic Python and statistics knowledge who want to apply deep learning to time series forecasting. If you are looking to solve business problems with modern neural networks and want practical experience with PyTorch, this course will help you build confidence and real-world skills.
