awesome-deep-learning
github.com/awesomelistsio/awesome-deep-learning ↗A curated list of awesome frameworks, libraries, tools, tutorials, research papers, and resources for deep learning. This list covers neural networks, model optimization, NLP, computer vision, and other deep learning applications.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me optimization and training resources from awesome-deep-learning"
Installation instructions →What's inside
Optimization and Training
- Adam Optimizer
An adaptive learning rate optimization algorithm.
- Batch Normalization
A technique to stabilize and accelerate the training of deep networks.
- Dropout
A regularization technique to prevent neural networks from overfitting.
- Learning Rate Schedulers
Techniques to adjust the learning rate during training for better convergence.
- Stochastic Gradient Descent (SGD)
A popular optimization method for training deep learning models.
Research Papers
- Attention Is All You Need (2017)
The paper that introduced the Transformer architecture.
- Deep Residual Learning for Image Recognition (2015)
The introduction of ResNet.
- Generative Adversarial Nets (2014)
Ian Goodfellow’s original GAN paper.
Natural Language Processing (NLP)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2018)
A transformer model for NLP tasks.
- GPT-3: Language Models are Few-Shot Learners (2020)
A large-scale generative language model.
- Hugging Face Transformers
A library for state-of-the-art NLP models like BERT, GPT, and RoBERTa.
- Seq2Seq Models
A neural network architecture for sequence-to-sequence learning tasks.
- spaCy
An NLP library for fast processing of text data.
Generative Models
- BigGAN: Large-Scale GAN Training for High-Fidelity Natural Image Synthesis (2018)
A generative model for producing high-resolution images.
- Diffusion Models
A generative model framework for image synthesis.
- StyleGAN
A GAN model for high-quality image synthesis.
- VAE: Variational Autoencoders (2013)
A model architecture for generating data through variational inference.
Frameworks and Libraries
- Caffe
A deep learning framework focused on convolutional neural networks (CNNs).
- JAX
A library for high-performance numerical computing and automatic differentiation.
- Keras
A high-level neural networks API, running on top of TensorFlow.
- MXNet
A deep learning framework known for its efficiency and scalability.
- PyTorch
A popular open-source deep learning framework that offers dynamic computation graphs.
- TensorFlow
An end-to-end open-source platform for machine learning and deep learning.
Neural Network Architectures
- Convolutional Neural Networks (CNNs)
A popular architecture for image and video analysis.
- Graph Neural Networks (GNNs)
A type of neural network for learning from graph-structured data.
- Long Short-Term Memory (LSTM)
A special type of RNN capable of learning long-term dependencies.
- Recurrent Neural Networks (RNNs)
A neural network architecture for sequence data, such as time series and text.
Computer Vision
- DeepLab
A model for semantic image segmentation.
- Detectron2
A high-performance framework for object detection and segmentation.
- VGGNet
A convolutional neural network known for its simplicity and performance in image classification.
- YOLO (You Only Look Once)
A state-of-the-art real-time object detection system.
Learning Resources
- Deep Learning Specialization on Coursera
A series of courses by Andrew Ng on deep learning.
- PyTorch Tutorials
Official tutorials for learning deep learning with PyTorch.
- Stanford CS230: Deep Learning
A comprehensive course on deep learning.
- TensorFlow Tutorials
Official TensorFlow tutorials for building deep learning models.
- The Deep Learning Book
A foundational book by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
Showing a sample of 45 resources. View the full list on GitHub →