Deep Learning logopeterindia.net
Knowledge Hub

Deep Learning: Frameworks, Datasets, GNNs & Learning Resources

Deep learning uses multi-layer neural networks to learn representations from raw data. This hub links to framework, dataset and GNN directories and to the main libraries, courses and books.

30 topics•5 categories•Updated October 2026

Deep Learning Directories on This Site

10 entries

Frameworks, GNNs and data.

01Deep Learning FrameworksTensorFlow, PyTorch, Keras, JAX, MXNet, PaddlePaddle and more. 02Graph Neural Network (GNN) FrameworksFrameworks for learning on graph-structured data. 03Graph Neural NetworksGCN, GAT, GraphSAGE and GIN explained. 04GNN LibrariesLibraries for graph neural networks. 05Data Sets for Machine & Deep LearningBenchmark and production datasets. 06Deep Learning PlatformsPlatforms for deep learning. 07Python Frameworks for AIPython frameworks for AI development. 08Generative Adversarial Networks (GANs)GAN papers, architectures such as StyleGAN, code and applications. 09Variational Autoencoders (VAEs)VAE theory, VQ-VAE, latent spaces, code and tutorials. 10Diffusion ModelsDDPM, Stable Diffusion, flow matching, image and video models, and libraries.

Core Frameworks

6 entries

Where most deep learning is written.

11PyTorchOpen-source deep learning framework widely used in research and production. 12TensorFlowGoogle's end-to-end machine learning platform. 13JAXComposable transformations of Python and NumPy programs for high-performance ML. 14KerasHigh-level deep learning API that runs on several backends. 15PyTorch GeometricLibrary for graph neural networks built on PyTorch. 16ONNXOpen format for exchanging models between frameworks.

Courses & Books

5 entries

Learn the theory and practice.

17Dive into Deep LearningFree interactive deep learning textbook with code. 18Deep Learning (Goodfellow, Bengio, Courville)Free online edition of the standard textbook. 19fast.aiFree practical deep learning courses. 20Stanford CS231nConvolutional neural networks for visual recognition. 21Attention Is All You NeedThe transformer paper.

Book from the Author

1 entries

Edge deployment of deep learning models.

22Deep Learning Model Optimization, Deployment and Improvement Techniques for Edge-native ApplicationsCo-authored by Gayathri and Pethuru Raj (Taylor & Francis); covers model compression, quantization, pruning, knowledge distillation and edge deployment.

Related Pages

8 entries

Neighbouring directories.

23Machine LearningMachine learning hub. 24Predictive AIPredictive AI and forecasting. 25Generative AIGenerative AI hub. 26Computer VisionComputer vision hub. 27Natural Language ProcessingNLP hub. 28Large Language ModelsLanguage models directory. 29Artificial IntelligenceAI hub. 305G Communication5G and 6G hub.

Frequently Asked Questions

What is deep learning?

Deep learning is a branch of machine learning that uses neural networks with many layers to learn features directly from raw data such as images, text and audio.

Which framework should I learn first?

PyTorch is the most common in research and increasingly in production; TensorFlow and Keras remain widely used, and JAX suits high-performance research.

What are graph neural networks?

Networks that learn from graph-structured data such as social networks and molecules; see the GNN Frameworks and Graph Neural Networks pages.

How do I learn deep learning?

Work through Dive into Deep Learning or fast.ai alongside a framework, and read the original papers once you have the basics.

How do I deploy models on edge devices?

Compress them with quantization, pruning and distillation; the author's book listed here covers these techniques.