Computer Science Reading List

This is the list of my favorite computer science books, articles, papers, and blogs.

1. Books

1.1. Data Structures and Algorithms

• The Art and Science of Java - Eric S. Roberts.

• Programming Abstractions in C++ - Eric S. Roberts.

• Algorithms Illuminated - Tim Roughgarden.

• Grokking Algorithms - Aditya Bhargava.

• Introduction to Algorithms - Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, Clifford Stein.

1.2. Computer Systems

• Computer Systems: A Programmer’s Perspective - Randal E. Bryant, David R. O’Hallaron.

• Principles of Computer System Design: An Introduction - Jerome H. Saltzer, M. Frans Kaashoek.

1.3. Theory

• Introduction to the Theory of Computation - Michael Sipser.

1.4. Artificial Intelligence

• Artificial Intelligence: A Modern Approach - Stuart Russell, Peter Norvig.

• Deep Learning - Ian Goodfellow, Yoshua Bengio, Aaron Courville.

• Dive into Deep Learning - Aston Zhang, Zack C. Lipton, Mu Li, Alex J. Smola.

• An Introduction to Statistical Learning - Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani.

• The Elements of Statistical Learning - Trevor Hastie, Robert Tibshirani, Jerome Friedman.

• Neural Networks and Deep Learning - Michael Nielsen.

• Hands-On Machine Learning with Scikit-Learn and TensorFlow - Aurelien Geron.

• Speech and Language Processing - Dan Jurafsky, James H. Martin.

• Introduction to Information Retrieval - Christopher D Manning, Prabhakar Raghavan, Hinrich Schutze.

• Mining of Massive Datasets - Jure Leskovec, Anand Rajaraman, Jeff Ullman.

• Reinforcement Learning: An Introduction - Richard S. Sutton, Andrew G. Barto.

• Natural Language Processing with Python - Steven Bird, Ewan Klein, Edward Loper.

• R for Data Science - Garrett Grolemund, Hadley Wickham.

2. Research Papers and Articles

2.1. Machine Learning

• Neural Ordinary Differential Equations.

• A Guide to Convolution Arithmetic for Deep Learning.

2.2. Computer Vision

• Fast R-CNN.

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

• Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation.

• SSD: Single Shot MultiBox Detector.

• You Only Look Once: Unified, Real-Time Object Detection.

• Feature Pyramid Networks for Object Detection.

• Mask R-CNN.

• U-Net: Convolutional Networks for Biomedical Image Segmentation.

• Densely Connected Convolutional Networks.

• Aggregated Residual Transformations for Deep Neural Networks.

• Focal Loss for Dense Object Detection.

• RetinaMask: Learning to Predict Masks Improves State-of-the-Art Single-Shot Detection for Free.

• FaceNet: A Unified Embedding for Face Recognition and Clustering.

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.

• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices.

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.

• EfficientDet: Scalable and Efficient Object Detection.

• Image-to-Image Translation with Conditional Adversarial Networks.

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks.

• Guided Image Generation with Conditional Invertible Neural Networks.

• Image Synthesis with a Single (Robust) Classifier.

• Convolutional Pose Machines.

• Hand Keypoint Detection in Single Images using Multiview Bootstrapping.

• Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields.

• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields.

• DensePose: Dense Human Pose Estimation In The Wild.

• DeepPose: Human Pose Estimation via Deep Neural Networks.

• Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding.

• RoadTagger: Robust Road Attribute Inference with Graph Neural Networks.

2.3. Natural Language Processing

• ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.

• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

• Efficient Estimation of Word Representations in Vector Space.

• Distributed Representations of Words and Phrases and their Compositionality.

• GloVe: Global Vectors for Word Representation.

• Sequence to Sequence Learning with Neural Networks.

• Efficient Transformers: A Survey.

• Attention Is All You Need.

• Effective Approaches to Attention-based Neural Machine Translation.

2.4. Reinforcement Learning

• Human-level Control through Deep Reinforcement Learning.

• Deep Reinforcement Learning for Power System Applications: An Overview.

2.5. Deep Learning Optimization

• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.

• Distilling the Knowledge in a Neural Network.

• To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression.

• Learning Both Weights and Connections for Efficient Neural Networks.

• Pruning Filters for Efficient ConvNets.

• Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks.

• SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and <0.5MB Model Size.

• mixup: Beyond Empirical Risk Minimization.

• Improved Regularization of Convolutional Neural Networks with Cutout.

2.6. Machine Learning Interpretability

• Visualizing and Understanding Convolutional Networks.

• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.

• Understanding Neural Networks Through Deep Visualization.

• Learning Deep Features for Discriminative Localization.

• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization.

2.7. AI for Climate Change

• Tackling Climate Change with Machine Learning.

• MetNet: A Neural Weather Model for Precipitation Forecasting.

• A Deep Learning and Gamification Approach to Improving Human-building Interaction and Energy Efficiency in Smart Infrastructure.

• Machine Vision for Natural Gas Methane Emissions Detection Using an Infrared Camera.

2.8. AI for Healthcare

• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning.

• CheXNeXt: Deep Learning for Chest Radiograph Diagnosis.

• MRNet: Deep-learning-assisted Diagnosis for Knee Magnetic Resonance Imaging.

• Deep Learning–Assisted Diagnosis of Cerebral Aneurysms Using the HeadXNet Model.

• International Evaluation of an AI System for Breast Cancer Screening.

2.9. Ethics of AI

• Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification.

• The Moral Machine Experiment.

3. Blogs

• The Stanford AI Lab Blog.

• deeplearning.ai.

• Facebook AI Blog.

• Google AI Blog.

• OpenAI Blog.

• Kaggle Blog.

• Machine Learning Mastery.

• PyImageSearch.