Learn Neural Network Architectures

Neural networks power modern AI applications, from image recognition to language processing. In this PyTorch deep learning tutorial, you'll learn how to build and train multiple neural network architectures including MLPs, CNNs, RNNs, transformers like BERT and GPT, and multimodal models like CLIP. You'll understand the design tradeoffs between different architectures, select the right model for specific AI problems, and implement them using PyTorch. By the end, you'll be able to profile model performance, debug common training issues, and leverage pretrained models for real-world applications in computer vision, natural language processing, and multimodal AI.

Syllabus

Introduction to Neural Network Architectures: Learn neural network architectures in PyTorch for tabular, image, sequential, and text data using MLPs, CNNs, and RNNs while profiling model performance.

Lesson: Introduction to Neural Network Architectures
Project: Build Neural Networks for Classifying Digits and Time-Series Predictions
Quiz: Intro to Neural Network Architectures Quiz

Advanced Neural Network Architectures: Learn about attention mechanisms and transformer architectures, such as BERT and GPT, for language tasks. Explore autoencoders and multimodal models using CLIP.

Lesson: Advanced Neural Network Architectures
Project: Classifying CIFAR-10 with Pretrained CLIP: Original vs Reconstructed Images
Quiz: Advanced Neural Network Architectures Quiz
Informational: Learn Neural Network Architectures Next Steps