Deep Learning with PyTorch and Neural Networks

About this course

Build deep learning models with PyTorch and develop practical skills in neural networks, computer vision, NLP, attention, and recommender systems. Progress from deep learning fundamentals to end-to-end AI workflows for image, text, translation, structured data, and personalized recommendations. This Specialization provides a structured path for learners who want to understand and apply modern deep learning techniques. You will begin by working with PyTorch tensors, gradients, hidden layers, neural networks, transfer learning, Jupyter Notebooks, and Google Colab. You will then prepare image datasets and build classifiers using MNIST and CIFAR-10 while learning how to configure layers, loss functions, training loops, and model evaluation workflows. You will extend these skills into natural language processing by developing text classification models and exploring transformer-based text generation. Finally, you will build encoder-decoder models with attention for translation, apply neural networks to tabular prediction, and explore collaborative filtering for recommender systems. Through progressive hands-on learning, you will develop the skills to build, train, evaluate, and optimize deep learning models across several widely used AI applications.

Prices, discounts and availability are set by Coursera. We may earn a commission when you purchase through links on this site.