This repository consist of various Deep Learning papers sorted by subareas. Currently this list is incomplete , I will add them overtime. I will also update this repository as I come across more papers that are interesting. Please feel free to make a pull request and add to the list.
- Patterns, predictions, and actions: A story about machine learning
- On Calibration of Modern Neural Networks
- Understanding deep learning requires rethinking generalization
- Label Refinery: Improving ImageNet Classification through Label Progression
- A Github Repository Repository that did a great job curating resources
- GPT-1: Improving Language Understanding by Generative Pre-Training
- GPT-2: Language Models are Unsupervised Multitask Learners
- GPT-3: Language Models are Few-Shot Learners
- Alexnet: ImageNet Classification with Deep Convolutional Neural Networks
- VGG: Very Deep Convolutional Networks for Large-Scale Image Recognition
- Resnet: Deep Residual Learning for Image Recognition
- Densenet: Densely Connected Convolutional Networks
- Mobilenet: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Squeezenet: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Multiple Instance Detection Network with Online Instance Classifier Refinement
- Weakly Supervised Object Detection with Segmentation Collaboration
- Weakly Supervised Deep Detection Networks
- Visualizing and Understanding Convolutional Networks
- Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
- LARGE BATCH TRAINING OF CONVOLUTIONAL NETWORKS : Introduces adaptive layerwise learning rates. Different learning rates for different layers.
- Accelerating Deep Learning by Focusing on the Biggest Losers
- MAML: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Reptile: On First-Order Meta-Learning Algorithms
- Recommending What Video to Watch Next: A Multitask Ranking System
- A Survey on Multi-Task Learning
- Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
- Zero-Shot Learning -- The Good, the Bad and the Ugly
- Transductive Unbiased Embedding for Zero-Shot Learning
- Semantic Autoencoder for Zero-Shot Learning
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning: Strategies for Improving Communication Efficiency
- Practical Secure Aggregation for Privacy-Preserving Machine Learning
- Active Federated Learning
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
- Federated Learning with Non-IID Data
- Advances and Open Problems in Federated Learning
- Addressing Class Imbalance in Federated Learning
- Evaluating and Testing Unintended Memorization in Neural Networks
- Privacy Considerations in Large Language Models
- A Survey of Model Compression and Acceleration for Deep Neural Networks
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Distilling the Knowledge in a Neural Network
- FitNets: Hints for Thin Deep Nets