Introduction to Deep Learning in PyTorch

What's inside

5 lessons · 1 project

• 01
  Deep Learning Fundamentals

  Learn the difference between shallow and dense neural networks and how forward propagation can be implemented from scratch.

  120 min
• 02
  Tensors and Autograd in PyTorch

  Learn the essentials of PyTorch tensors, including creation, shapes/dtypes, reshaping, stacking, and broadcasting—plus a gentle intro to autograd. Practice NumPy interop and when to enable or skip gradient tracking, all in a fast, CPU-only environment.

  120 min
• 03
  Building Neural Networks with nn.Sequential

  Learn to construct neural networks using PyTorch's nn.Sequential container. Build regression models with nn.Linear layers and activation functions, prepare real-world tabular data, and understand model parameters before training begins.

  120 min
• 04
  Training Neural Networks

  Implement the complete training workflow in PyTorch, from creating DataLoaders for efficient batching to building the training loop with optimizers and loss functions. Train models through multiple epochs while tracking progress, then evaluate performance using interpretable metrics like RMSE and R². Visualize training curves and prediction accuracy, and learn to save and load trained models for future use.

  120 min
• 05
  Deep Networks and Regularization

  Build deep neural networks for binary classification using sigmoid activation and BCE loss. Diagnose overfitting by comparing training and validation curves, then fix it with batch normalization and dropout regularization. Implement early stopping to automatically save your best model, and evaluate performance using confusion matrices, precision, and recall. Apply these professional techniques to predict Titanic survival while maintaining proper train/validation/test splits throughout.

  120 min
• 06
  Guided Project: Predicting Listing Gains in the Indian IPO Market Using PyTorch Project

  For this project, you'll work as a data scientist for an investment firm analyzing the Indian IPO market. You'll build a deep learning model using PyTorch to predict listing gains, applying skills in data exploration, preprocessing, advanced regularization, and comprehensive evaluation.

  120 min

Master skills faster with Dataquest

Go from zero to job-ready

Learn exactly what you need to achieve your goal. Don't waste time on unrelated lessons.

Build your project portfolio

Build confidence with our in-depth projects, and show off your data skills.

Challenge yourself with exercises

Work with real data from day one with interactive lessons and hands-on exercises.

Showcase your path certification

Share the evidence of your hard work with your network and potential employers.