This page contains resources, blogs, projects, papers, codes, links and other materials needed to get exposure in Deep Learning. Feel free to share it to people interested in this domain.
- Andrej Karpathy
- Christopher Olah
- Denny Britz
- Tim Dettmers
- Jon Gauthier
- Jonas Degrave
- Deep Learning.net
- Charles H Martin
- Thomas Kipf
- Jason Brownlee
- Adrian Rosebrock
- Deep Learning - Google
- Deep Learning Specialization - Andrew NG
- CS229 Machine Learning - Andrew NG
- Deep Learning - Udacity
- Deep Learning at Oxford - Nando de Freitas (University of Oxford)
- Neural Networks for Machine Learning - Geoffrey Hinton (Google, University of Toronto)
- Deep Learning for Computer Vision - Rob Fergus (Facebook, NYU)
- Learning from Data - Yasser Abu-Mostafa (Caltech)
- Deep Learning for Natural Language Processing (Stanford)
- NVIDIA Deep Learning Institute
- Deep Learning for Business - Jong-Moon Chung
- Deep Learning in Python - Data Camp
- Machine Learning for Musicians and Artists - Goldsmiths, University of London
- 6.S191: Introduction to Deep Learning - Massachusetts Institute of Technology
- 6.S094: Deep Learning for Self-Driving Cars - Massachusetts Institute of Technology
- Deep Learning for Natural Language Processing - University of Oxford
- CS231n: Convolutional Neural Networks for Visual Recognition - Stanford University
- Learn TensorFlow and deep learning, without a Ph.D. - Google
- Deep Learning A-Z™: Hands-On Artificial Neural Networks - Udemy
- Zero to Deep Learning™ with Python and Keras - Udemy
- Deep Learning Prerequisites: The Numpy Stack in Python - Udemy
- Data Science: Deep Learning in Python - Udemy
- Deep Learning Prerequisites: Linear Regression in Python - Udemy
- Deep Learning Prerequisites: Logistic Regression in Python - Udemy
- Deep Learning: Convolutional Neural Networks in Python - Udemy
- Data Science: Deep Learning in Python - Udemy
- Modern Deep Learning in Python - Udemy
- Deep Learning: Recurrent Neural Networks in Python - Udemy
- Unsupervised Deep Learning in Python - Udemy
- Natural Language Processing with Deep Learning in Python - Udemy
- Unleash Deep Learning: Begin Visually with Caffe and DIGITS - Udemy
- GPUs and Machine Learning: A Look at cuDNN- Sharan Chetlur (NVIDIA)
- Deep Learning at Scale - Ren Wu (Baidu)
- Deep Learning: What's Next - Andrew Ng (Baidu)
- Keras, is a Deep Learning library for Python, that is simple, modular, and extensible. Created by Franchois Chollet, Artificial Intelligence Researcher, Google.
- Caffe, created by Yangqing Jia and developed by the Berkeley Vision and Learning Center (BVLC) and by community contributors.
- Theano, primarily developed by a machine learning group at the Université de Montréal.
- TensorFlow, originally developed by the Google Brain team for internal Google use before being released under the Apache 2.0 open source license on November 9, 2015.
- MXNet, an open-source deep learning framework that allows you to define, train, and deploy deep neural networks on a wide array of devices, from cloud infrastructure to mobile devices.
- Torch, a scientific computing framework with wide support for machine learning algorithms that puts GPUs first.
- sklearn-theano, OverFeat and GoogleNet feature extractor for Python.
- Deep Learning book, by Ian Goodfellow and Yoshua Bengio and Aaron Courville.
- Deep learning, Yann LeCun, Yoshua Bengio and Geoffrey Hinton.
- A Taxonomy of Deep Convolutional Neural Nets for Computer Vision, Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri, Nikita Prabhu, Srinivas S S Kruthiventi, R. Venkatesh Babu.
- A Critical Review of Recurrent Neural Networks for Sequence Learning, Zachary C. Lipton, John Berkowitz.
Must read papers
- Deep Sparse Rectifier Neural Networks - [Paper], Xavier Glorot, Antoine Bordes, Yoshua Bengio.
- Efficient Backprop - [Paper], Yaan LeCun et al.
- VGGNet - Very Deep Convolutional Networks for Large-Scale Image Recognition - [Home], [arXiv], [Slides], [PDF], [GitHub], [TensorFlow], [Keras VGG16], [Keras VGG19]
- GoogleNet - Going Deeper with Convolutions - [arXiv], [GitHub], [Torch], [Keras], [Blog]
- Inception-V2 - Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift - [arXiv], [GitHub], [Keras], [Blog]
- Inception-V3 - Rethinking the Inception Architecture for Computer Vision - [arXiv], [Torch], [TensorFlow], [Blog], [Keras]
- Inception-V4 - Inception-Resnet And The Impact Of Residual Connections On Learning - [arXiv], [Keras], [Torch]
- ResNet - Deep Residual Learning for Image Recognition - [arXiv], [Torch], [Torch], [Keras]
- ResNet V2 - Identity Mappings in Deep Residual Networks - [arXiv], [GitHub], [GitHub]
- ResNeXt - Aggregated Residual Transformations for Deep Neural Networks - [arXiv], [GitHub], [Torch]
Deep Learning for Computer Vision
- DenseCap: Fully Convolutional Localization Networks for Dense Captioning - [Page], [GitHub], [arXiv]
- Deep Visual-Semantic Alignments for Generating Image Descriptions - [PDF], [GitHub], [Presentation]
Deep Learning for Face Recognition
- DeepID - Deep Learning Face Representation from Predicting 10,000 Classes - [Paper], [GitHub]
- DeepID2 - Deep Learning Face Representation by Joint Identification-Verification - [arXiv]
- DeepID3 - Face Recognition with Very Deep Neural Networks - [arXiv]
- Learning Face Representation from Scratch - [arXiv]
- Face Search at Scale: 80 Million Gallery - [arXiv]
- A Discriminative Feature Learning Approach for Deep Face Recognition - [arXiv]
- One Millisecond Face Alignment with an Ensemble of Regression Trees - [arXiv]
- DeepFace - Closing the Gap to Human-Level Performance in Face Verification - [Paper], [Slides], [GitHub]
- Deep Face Recognition - Closing the Gap to Human-Level Performance in Face Verification - [Paper], [Home], [Keras]
- FaceNet - A Unified Embedding for Face Recognition and Clustering - [Paper], [TensorFlow], [GitHub]
- Targeting Ultimate Accuracy - Face Recognition via Deep Embedding - [Paper]
Deep Learning for Robotics
- A Survey of Machine Learning Approaches to Robotic Path-Planning - [Paper]
- Deep Learning Driven Visual Path Prediction from a Single Image - [arXiv]
- A Novel Path Planning Method for Biomimetic Robot based on Deep Learning - [Link]
- DeepVO: A Deep Learning approach for Monocular Visual Odometry - [arXiv]
- An Improved Q-learning Algorithm for Path-Planning of a Mobile Robot - [Paper]
- Optical Flow and Deep Learning Based Approach to Visual Odometry - [Thesis]
- Learning Visual Odometry with a Convolutional Network - [Paper]
- Learning to See by Moving - [arXiv]
Deep Learning for Music
- Music Generation with Deep Learning - [Paper]
- Deep Learning for Music - [Paper]
- GRUV: Algorithmic Music Generation using Recurrent Neural Networks - [Paper], [GitHub]
- A Recurrent Neural Network Music Generation Tutorial - [Tutorial]
- Composing Music With Recurrent Neural Networks - [Tutorial]
- Modeling and generating sequences of polyphonic music with the RNN-RBM - [Tutorial]
- Deep learning for assisting the process of music composition - [Tuturial]
- Using machine learning to generate music - [Blog]
- WaveNet: A Generative Model for Raw Audio - [Blog]
- Deep Learning for Music - [Blog]
- Generating sound with recurrent neural networks - [Blog]
- Generating Multi-track Music with Deep Learning - [Blog]
Deep Learning for Fine Grained Recognition
- Fine-Grained Plant Classification Using Convolutional Neural Networks for Feature Extraction - [Paper]
- Fine-tuning Deep Convolutional Networks for Plant Recognition - [Paper]
- Plant species classification using deep convolutional neural network - [Paper]
- Plant classification using convolutional neural networks - [Paper]
- Deep-plant: Plant identification with convolutional neural networks - [Paper]
- Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification - [Paper]
- Plant Leaf Identification via A Growing Convolution Neural Network with Progressive Sample Learning - [Paper]
- DeepFood - Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment - [arXiv]
- Im2Calories - towards an automated mobile vision food diary - [Paper]
- Food Image Recognition by Using Convolutional Neural Networks (CNNs) - [arXiv]
- Food Classification with Deep Learning in Keras / Tensorflow - [Blog], [GitHub]
- Automatic Instrument Recognition in Polyphonic Music Using Convolutional Neural Networks - [arXiv], [GitHub]
Musical Instrument Recognition
- Deep Convolutional Networks on the Pitch Spiral for Musical Instrument Recognition - [Paper], [GitHub]
- Deep Learning for Logo Recognition - [arXiv]
In case if you found something useful to add to this article or you found a bug in the code or would like to improve some points mentioned, feel free to write it down in the comments. Hope you found something useful here.