Recommended Online Courses
Most of us professionals have very little time and stamina to read through books. We would always prefer to go through some videos and learn the subject quickly. Here are some of the online courses that I found useful.
We have many sources of online video tutorials. Coursera, Udacity, edX, Udemy, Edureka are the most popular. Each of them have good set of tutorials on most subjects that one could think of. But when it comes to machine learning, nobody can beat Coursera, that is headed by Andrew Ng himself.
Useful Reference Books
Tutorials and blogs are great for an introduction to the subject and to keep in touch with the latest developments. But if you want to go deeper and master it inside-out, you have no alternative to books. Here are some of the useful text books and cookbooks that can help you master the subject.
Textbooks are required to give a thorough introduction to a subject, elaborating on all the fundamental concepts. Here are some that I found very useful.
Text Books give us a good understanding of the subject. But, often it helps to get some ready solutions to common problems. That helps us from re-inventing the wheel. The cookbooks help us with that. Here are some that can help us in that.
Some of the great authors have contributed to the literature. These may not directly help you understand the technical aspects of the subject. But they will surely help broaden your perspective.
Github is the home of creativity. Techies from all over the world have deposited their creations into this ocean of code. If one can search for it, almost all problems that we face already have a solution on Github. Here are some of the repositories on Github that I found useful. This list will continue to grow as I find more and more of these.
Significant Research Papers
There is no other way to keep up with the latest trends in the developments in any domain. Research papers help us understand the sequence and basis of developments over the years. Below are some of the important research papers published over the last few years. Some of them mark important milestones in the development. Others form a good overview of the developments around the time. Anyone interested in a deeper understanding of the subject will surely want to read through them.
- Hinton, Geoffrey, et al. "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups." IEEE Signal Processing Magazine 29.6 (2012)
- Amodei, Dario, et al. "Deep speech 2: End-to-end speech recognition in english and mandarin. 2015"
- W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, G. Zweig "Achieving Human Parity in Conversational Speech Recognition. 2016"
Deep Learning Models
- Le, Quoc V. "Building high-level features using large scale unsupervised learning." 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 2013.
- Kingma, Diederik P., and Max Welling. "Auto-encoding variational bayes." (2013)
- Goodfellow, Ian, et al. "Generative adversarial nets." Advances in Neural Information Processing Systems. 2014
- Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." (2015)
- Gregor, Karol, et al. "DRAW: A recurrent neural network for image generation." (2015)
- Oord, Aaron van den, Nal Kalchbrenner, and Koray Kavukcuoglu. "Pixel recurrent neural networks." (2016)
- Oord, Aaron van den, et al. "Conditional image generation with PixelCNN decoders." (2016)
Recurrent Neural Networks
Neural Machine Tuning
- Mnih, Volodymyr, et al. "Playing atari with deep reinforcement learning." (2013)
- Mnih, Volodymyr, et al. "Human-level control through deep reinforcement learning." Nature 518.7540 (2015)
- Wang, Ziyu, Nando de Freitas, and Marc Lanctot. "Dueling network architectures for deep reinforcement learning." (2015)
- Mnih, Volodymyr, et al. "Asynchronous methods for deep reinforcement learning." (2016)Lillicrap, Timothy P., et al. "Continuous control with deep reinforcement learning." (2015)
- Gu, Shixiang, et al. "Continuous Deep Q-Learning with Model-based Acceleration." (2016)
- Schulman, John, et al. "Trust region policy optimization." CoRR, abs/1502.05477 (2015)
- Silver, David, et al. "Mastering the game of Go with deep neural networks and tree search." Nature 529.7587 (2016)
Deep Transfer Learning / Lifelong Learning
One Shot Deep Learning
- Lake, Brenden M., Ruslan Salakhutdinov, and Joshua B. Tenenbaum. "Human-level concept learning through probabilistic program induction." (2015)
- Santoro, Adam, et al. "One-shot Learning with Memory-Augmented Neural Networks." (2016)
- Hariharan, Bharath, and Ross Girshick. "Low-shot visual object recognition." (2016)
- Antoine Bordes, et al. "Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing." (2012)
- Ankit Kumar, et al. "“Ask Me Anything: Dynamic Memory Networks for Natural Language Processing." (2015)
- Yoon Kim, et al. "Character-Aware Neural Language Models." NIPS(2015)
- Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014
- He, Kaiming, et al. "Spatial pyramid pooling in deep convolutional networks for visual recognition." European Conference on Computer Vision. Springer International Publishing, 2014
- Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE International Conference on Computer Vision. 2015
- Ren, Shaoqing, et al. "Faster R-CNN: Towards real-time object detection with region proposal networks." Advances in neural information processing systems. 2015.
- Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." (2015)
- Dai, Jifeng, et al. "R-FCN: Object Detection via Region-based Fully Convolutional Networks." (2016)
- He, Gkioxari, et al. "Mask R-CNN" (2017)