markdown ML，DL，AI，Web /数据挖掘，图形资源

Posted 2021-05-06

### Lists of Resources:

* deeplearning.net: Lists of books, papers, libraries/packages, datasets etc.: http://deeplearning.net/
* The Best Deep Learning Resources: https://medium.com/@rayalez/best-deep-learning-resources-76b24c67f9e
* Awesome DL: https://github.com/ChristosChristofidis/awesome-deep-learning
* Open Source ML Degree: https://github.com/Nixonite/open-source-machine-learning-degree
* Awesome Public Datasets: https://github.com/awesomedata/awesome-public-datasets
* Machine learning for Data Engineers: https://github.com/ZuzooVn/machine-learning-for-software-engineers#beginner-books
* List of free must-read ML/DL books: http://houseofbots.com/news-detail/2461-4-list-of-free-must-read-machine-learning-books
* Machine Learning Links & Lessons Learned: https://github.com/adeshpande3/Machine-Learning-Links-And-Lessons-Learned
* A Guide to Machine Learning PhDs: https://blog.ycombinator.com/a-guide-to-machine-learning-phds/

### ML Resources

* Victor Lavrenko's awesome youtube videos: https://www.youtube.com/user/victorlavrenko/playlists?view=1&sort=dd&shelf_id=0
* K-Means clustering in Python: https://mubaris.com/2017/10/01/kmeans-clustering-in-python/

### DL Resources

* Stanford 2017: Theories of Deep Learning (STATS 385): https://stats385.github.io/readings
* Awesome Deep Learning: Almost all resources can be found here: https://github.com/ChristosChristofidis/awesome-deep-learning
* Learning Deep Learning - My Top-Five List: http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/
* Tel Aviv Deep Learning Bootcamp: 
	- Website: http://deep-ml.com/
	- Github: https://github.com/QuantScientist/Deep-Learning-Boot-Camp
	- PyTorch notebooks: https://github.com/QuantScientist/Deep-Learning-Boot-Camp/tree/master/day02-PyTORCH-and-PyCUDA/PyTorch
	- Full Docker image: https://github.com/QuantScientist/Deep-Learning-Boot-Camp/tree/master/docker
* Oxford CS DeepNLP 2017 github: https://github.com/oxford-cs-deepnlp-2017/lectures
* Capsule Networks (CapsNets) - Geoffrey Hinton:
	- Article: https://www.techleer.com/articles/447-a-nice-easy-tutorial-to-follow-on-capsule-networks-based-on-sabour-frosst-and-hintons-paper/
	- Video: https://www.youtube.com/watch?time_continue=4&v=pPN8d0E3900
	- Hinton video: https://www.youtube.com/watch?v=6S1_WqE55UQ
	- Paper: https://arxiv.org/abs/1710.09829
	- Implementations:
		- TensorFlow (covered in video above): https://github.com/ageron/handson-ml/blob/master/extra_capsnets.ipynb
		- Another TensorFlow implementation: https://github.com/naturomics/CapsNet-Tensorflow
		- Keras (TF backend): https://github.com/XifengGuo/CapsNet-Keras
		- PyTorch: https://github.com/gram-ai/capsule-networks
* GANs for beginners: https://www.oreilly.com/learning/generative-adversarial-networks-for-beginners
* Goodfellow - NIPS GAN tutorial
	- Video: https://www.youtube.com/watch?v=YpdP_0-IEOw
	- Text: https://arxiv.org/pdf/1701.00160.pdf 

### AI/Reinforcement Learning Resources

* (Berkeley AI Research: BAIR): Learning Diverse Skills via Maximum Entropy Deep Reinforcement Learning: http://bair.berkeley.edu/blog/2017/10/06/soft-q-learning/
* Denny Britz codebase (referencing Sutton's book and David Silver's lectures): https://github.com/dennybritz/reinforcement-learning
* John Schulman's Deep RL Bootcamp:
	- Website: https://sites.google.com/view/deep-rl-bootcamp/lectures (videos downloaded)
	- Summary: https://github.com/williamFalcon/DeepRLHacks
* Intel coach: setup to practice reinforcement learning (works on top of openai gym):
	- article: https://ai.intel.com/reinforcement-learning-coach-intel/
	- github: https://github.com/NervanaSystems/coach

### Bayesian Methods/ Prob Graphical Models/ Networks/ Graphs Resources:

* Probabilistic Graphical Models with pgmpy: https://people.duke.edu/~ccc14/sta-663-2017/16_PGM.html
* Hamiltonian Monte Carlo explained: http://arogozhnikov.github.io/2016/12/19/markov_chain_monte_carlo.html
* Generalizing Hamiltonian Monte Carlo with Neural Networks: https://arxiv.org/abs/1711.09268
* VideoLectures.net - Graphical Models: http://videolectures.net/epsrcws08_ghahramani_gm/?q=graphical+model
* VideoLectures.net - Undirected Graphical Models: http://videolectures.net/deeplearning2015_courville_graphical_models/
* PyMC3
	- Getting started guide: http://docs.pymc.io/notebooks/getting_started#Installation
	- Probabilistic Programming Tutorial: https://github.com/fonnesbeck/PyMC3_DataScienceLA
	- Probabilistic Programming and Bayesian Methods for hackers: https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers
	- PyMC3 port of the book Doing Bayesian Analysis: https://github.com/aloctavodia/Doing_bayesian_data_analysis
	- PyMC3 port of Statistical Rethinking, McElreath: https://github.com/aloctavodia/Statistical-Rethinking-with-Python-and-PyMC3
	- Bayesian cognitive modelling in PyMC3: https://github.com/junpenglao/Bayesian-Cognitive-Modeling-in-Pymc3
	- Bayesian Analysis with Python book (with PyMC3): https://www.packtpub.com/big-data-and-business-intelligence/bayesian-analysis-python

### Data Science Resources:

* Kaggle: Hands-on Data Science Education: https://www.kaggle.com/learn/overview

### Online Books

* Jordan - Intro to Probabilistic Graphical Models: http://people.eecs.berkeley.edu/~jordan/prelims/
* Duke - STA-663-2017: https://people.duke.edu/~ccc14/sta-663-2017/index.html
* Nielson: Neural Networks and Deep Learning: http://neuralnetworksanddeeplearning.com/
* Goodfellow, Bengio, Courville: The Deep Learning Book: http://www.deeplearningbook.org/
* Mackworth, Poole - AI Foundations of Computational Agents 2E - http://artint.info/2e/html/ArtInt2e.html
* Artificial Intelligence (gitbook): https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/
* Design Patterns for Deep Learning Architectures: https://www.datasciencecentral.com/profiles/blogs/design-patterns-for-deep-learning-architectures
* Probabilistic Programming and Bayesian Methods for Hackers
	- book site: http://camdavidsonpilon.github.io/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/
	- code: https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers
	- jupyter nbviewer: http://nbviewer.jupyter.org/github/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/blob/master/Prologue/Prologue.ipynb

### Books related:

* Sutton & Barto: Reinforcement Learning - 2Ed - Python Code:
	- github: https://github.com/ShangtongZhang/reinforcement-learning-an-introduction
* Bishop - Pattern Recognition & Machine Learning
	- python code: https://github.com/yiboyang/PRMLPY
* Murphy - Machine Learning: A Probabilistic Perspective
	- python 3 code: https://github.com/probml/pyprobml
	- solutions: https://github.com/astahlman/MLaPP
* Tibshirani et al - Introduction to Statistical Learning:
	- python code: https://github.com/JWarmenhoven/ISLR-python
	- videos: http://www.dataschool.io/15-hours-of-expert-machine-learning-videos/
	- course: Stanford Lagunita
* McElreath - Statistical Rethingking
	- python (uses PyMC3) code: https://github.com/aloctavodia/Statistical-Rethinking-with-Python-and-PyMC3
* Kruschke - Doing Bayesian Analysis (R, JAGS, STAN)
	- python code: https://github.com/JWarmenhoven/DBDA
	- videos: https://sites.google.com/site/doingbayesiandataanalysis/videos
* Lee, Wagenmakers - Bayesian Cognitive Modelling
	- website: https://bayesmodels.com/
	- python PyMC3 code: https://github.com/pymc-devs/resources/tree/master/BCM
* Russell, Norvig - AI: A Modern Approach
	- python code: https://github.com/aimacode/aima-python

### Online course related:

#### Dedicated Learning Platforms:

* Nvidia Deep Learning Institute: https://www.nvidia.com/en-us/deep-learning-ai/education/
* Super Data Science (Kirill Eremenko): https://www.superdatascience.com/
* Datacamp - Deep Learning in Python: https://www.datacamp.com/courses/deep-learning-in-python
* Refactored.ai - quite a few paths & courses: https://refactored.ai/
* Metacademy: https://metacademy.org/roadmaps/

#### Compiled

* Ng Machine Learning: Python code: http://www.johnwittenauer.net/machine-learning-exercises-in-python-part-1/
* Hugo Larochelle' Sherbrooke course and resources: http://info.usherbrooke.ca/hlarochelle/neural_networks/content.html
* MIT Deep Learning for Self-Driving Cars resources: https://selfdrivingcars.mit.edu/
* Stanford Unsupervised Featur Learning and Deep Learning Tutorial: http://ufldl.stanford.edu/tutorial/
* Virginia tech course and youtube videos
	- https://computing.ece.vt.edu/~f15ece6504/
	- https://www.youtube.com/channel/UCLGwlAK4v2j35Ie8dbSDo4Q/playlists
* Intel ML course: https://software.intel.com/en-us/ai-academy/students/kits/machine-learning-501
* Intel DL course: https://software.intel.com/en-us/ai-academy/students/kits/deep-learning-501?utm_source=Facebook.com&utm_medium=Social%20Media&utm_campaign=AI_EMEA_Q1_18_FB_DL
* Google ML course: https://developers.google.com/machine-learning/crash-course/ml-intro
* University of Buffalo courses: 
	- Intro to ML: http://www.cedar.buffalo.edu/~srihari/CSE574/
	- Deep Learning: http://www.cedar.buffalo.edu/~srihari/CSE676/
	- Probabilistic Graphical Models: http://www.cedar.buffalo.edu/~srihari/CSE674/
* Caltech: Probabilistic Graphical Models: http://courses.cms.caltech.edu/cs155/index.html#details 
* CMU: Probabilistic Graphical Models: http://www.cs.cmu.edu/~epxing/Class/10708/lecture.html
* U. Washington: Linear Optimization: https://sites.math.washington.edu/~burke/crs/407/index.html
* CMU: Tom Mitchell: Machine Learning: http://www.cs.cmu.edu/%7Etom/10701_sp11/lectures.shtml

### Tutorials:

* Machine learning with Scikit-Learn: https://www.youtube.com/playlist?list=PLonlF40eS6nynU5ayxghbz2QpDsUAyCVF
* UFLDL Tutorial on Machine Learning: http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutorial
* Deep Reinforcement Learning tutorials: (Python): https://www.youtube.com/playlist?list=PLXO45tsB95cIplu-fLMpUEEZTwrDNh6Ba
* Pydata-annarbor2017 DL Tutorial (TensorFlow): https://github.com/rasbt/pydata-annarbor2017-dl-tutorial
* Practical Python and OpenCV based computer vision: https://www.pyimagesearch.com/practical-python-opencv/
* Tutorial slides by Andrew Moore (CMU): https://www.autonlab.org/tutorials
* The evolution of Gradient Descent: https://github.com/llSourcell/The_evolution_of_gradient_descent/
* Backprop is just Steepest Descent with Automatic Differentiation: https://idontgetoutmuch.wordpress.com/2013/10/13/backpropogation-is-just-steepest-descent-with-automatic-differentiation-2/
* Learn Data Science (notebook based): https://github.com/nborwankar/LearnDataScience
* Tirtho: PythonMachineLearning: https://github.com/tirthajyoti/PythonMachineLearning

### Blogs

* AdventuresInMachineLearning: RNN-LSTM http://adventuresinmachinelearning.com/recurrent-neural-networks-lstm-tutorial-tensorflow/
* iamtrask: LSTM-RNN Part 1: https://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/
* Understanding emotions: Keras & PyTorch: https://medium.com/huggingface/understanding-emotions-from-keras-to-pytorch-3ccb61d5a983
* Inverse Reinforcement Learning: https://thinkingwires.com/posts/2018-02-13-irl-tutorial-1.html?utm_campaign=Revue+newsletter&utm_medium=Newsletter&utm_source=The+Wild+Week+in+AI
* Dissecting Reinforcement Learning Part 1: https://mpatacchiola.github.io/blog/2016/12/09/dissecting-reinforcement-learning.html
* List of Data Science, DL, ML blogs: https://github.com/dataquestio/data-science-blogs
* distill.pub (very clear and good examples): https://distill.pub/
* Peter's Notes: http://peterroelants.github.io/
* Andrej Karpathy's Blog:
	- The Unreasonable Effectiveness of Recurrent Neural Nets: http://karpathy.github.io/2015/05/21/rnn-effectiveness/
* Colah's Blog:
	- Understanding LSTM networks
* WildML:
	- Implementing an NN from scratch in Python: http://www.wildml.com/2015/09/implementing-a-neural-network-from-scratch/
	- RNN Tutorial, Part 1: http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/
	- RNN Tutorial, Part 2: http://www.wildml.com/page/2/
	- RNN Tutorial, Part 3: http://www.wildml.com/2015/10/recurrent-neural-networks-tutorial-part-3-backpropagation-through-time-and-vanishing-gradients/
	- RNN Tutorial, Part 4: http://www.wildml.com/2015/10/recurrent-neural-network-tutorial-part-4-implementing-a-grulstm-rnn-with-python-and-theano/
	- Learning Reinforcement Learning: http://www.wildml.com/2016/10/learning-reinforcement-learning/
	  (github code: https://github.com/dennybritz/reinforcement-learning)
	- Intro to Learning to trade with Reinforcement Learning: http://www.wildml.com/
* Machine Learning Mastery:
	- Time series prediction with LSTM RNNs using Keras: https://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural-networks-python-keras/
	- Time series forecasting with LSTM in Python: https://machinelearningmastery.com/time-series-forecasting-long-short-term-memory-network-python/
	- Multivariate time series forecasting with LSTM in Python: https://machinelearningmastery.com/multivariate-time-series-forecasting-lstms-keras/
	- How to start on small projects & compete on Kaggle: https://machinelearningmastery.com/how-a-beginner-used-small-projects-to-get-started-in-machine-learning-and-compete-on-kaggle/

### Research Groups etc.

* deeplearning.net list: http://deeplearning.net/deep-learning-research-groups-and-labs/

### Papers

#### Classics

* Efficient BackProp (LeCun et al.): http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf
* Unsupervised Image-to-Image Translation Networks (amazing results for converting images from rainy to sunny, night to day etc.) - https://arxiv.org/abs/1703.00848
	- repo (UNIT) : https://github.com/mingyuliutw/unit
* Graves, Schmidhuber: Multi-dimensional RNNs: https://arxiv.org/pdf/0705.2011v1.pdf

#### Important co.s

* (Facebook Research) Poincare Embeddings for Learning Hierarchical Representations: https://arxiv.org/abs/1705.08039
* (Deepmind PathNet): 
	- website: https://deepmind.com/research/publications/pathnet-evolution-channels-gradient-descent-super-neural-networks/
	- paper: https://arxiv.org/pdf/1701.08734.pdf
* (Deepmind) Rainbow: Combining Improvements in Deep Reinforcement Learning: https://arxiv.org/abs/1710.02298
* (Deepmind) Asynchronous Methods for Deep Reinforcement Learning: https://arxiv.org/abs/1602.01783

#### Others 

* Deep vs. shallow networks : An approximation theory perspective: https://arxiv.org/abs/1608.03287
* Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent: https://arxiv.org/abs/1711.10456v1
* W-Net: A Deep Model for Fully Unsupervised Image Segmentation: https://arxiv.org/abs/1711.08506
* StarGAN: Unified GANs for Multi-Domain Image-to-Image Translation: https://arxiv.org/abs/1711.09020
* StarGAN implementation repo: https://github.com/yunjey/StarGAN
* TF Boosted Trees: A scalable TensorFlow based framework for gradient boosting: https://arxiv.org/abs/1710.11555v1
* DeepXplore: Automated Whitebox Testing of Deep Learning Systems: https://arxiv.org/abs/1705.06640
* Searching for Activation Functions: https://arxiv.org/abs/1710.05941
* Dilated RNNs: https://arxiv.org/abs/1710.02224
* Multi-task Sequence to Sequence Learning: https://arxiv.org/abs/1511.06114
* Designing Neural Network Architectures using Reinforcement Learning: https://arxiv.org/abs/1611.02167
* Bayesian SegNet: https://arxiv.org/pdf/1511.02680.pdf
* Algebraic Machine Learning (as opposed to Statistical): https://arxiv.org/pdf/1803.05252.pdf

### Dl/Ml Pipeline building:

* End to end pipeline: https://spandan-madan.github.io/DeepLearningProject/
* DeepDetect: Open Source DL Server: https://deepdetect.com/
* OpenAI - Fitting larger networks into memory (using https://github.com/openai/gradient-checkpointing): https://medium.com/@yaroslavvb/fitting-larger-networks-into-memory-583e3c758ff9
* Building a Facial Recognition Pipeline with DL in TensorFlow: https://hackernoon.com/building-a-facial-recognition-pipeline-with-deep-learning-in-tensorflow-66e7645015b8
* Tensorflow: How to optimise your input pipeline with queues and multi-threading: https://blog.metaflow.fr/tensorflow-how-to-optimise-your-input-pipeline-with-queues-and-multi-threading-e7c3874157e0
* Continuously Train and Deploy Spark ML and Tensorflow AI Models from Jupyter Notebook to Production: https://www.youtube.com/watch?v=swiPWUxBvSc&feature=share
* PipelineAI: https://github.com/PipelineAI/pipeline (Compatible with Python, C++, SparkML, Tensorflow, MXNet etc.)
	- PipelineAI notebooks: https://github.com/PipelineAI/notebooks/tree/master/55_Google_AppliedAI
* Run Keras Models in Parallel on Apache Spark using Apache SystemML: https://www.coursera.org/learn/ai/lecture/uqAKN/run-keras-models-in-parallel-on-apache-spark-using-apache-systemml

### DL/ML API/app building:

#### REST APIs

* Building a simple Keras + deep learning REST API: https://blog.keras.io/building-a-simple-keras-deep-learning-rest-api.html
* A simple REST API (uses web.py): https://www.artificialworlds.net/presentations/a-basic-rest-api-reboot/a-basic-rest-api-reboot.html#

#### Typescript/Javascript APIs:

* Building a real-time smile detection app with Deeplearn.js & Angular: https://medium.com/the-unitgb/building-a-real-time-smile-detection-app-with-deeplearn-js-820eb48e09b7


### Specific library/ package/ framework resources:

#### Tensorflow

* Stanford CS 20: TensorFlow Tutorials: 
	- Website: http://web.stanford.edu/class/cs20si/syllabus.html
	- Github: https://github.com/chiphuyen/stanford-tensorflow-tutorials
* Pro Deep Learning with TensorFlow: https://github.com/Apress/pro-deep-learning-w-tensorflow
* Running CapsuleNet (Hinton) on TensorFlow: https://medium.com/botsupply/running-capsulenet-on-tensorflow-1099f5c67189
* Deep Learning from Scratch: Theory and Implementation using TensorFlow: http://www.deepideas.net/deep-learning-from-scratch-theory-and-implementation/
* Effective TensorFlow: https://github.com/vahidk/EffectiveTensorflow#stable
* Kadenze - Creative Applications of Deep Learning with TensorFlow: https://www.kadenze.com/programs/creative-applications-of-deep-learning-with-tensorflow
* Curated list of Dedicated Resources: https://www.techleer.com/articles/419-a-curated-list-of-dedicated-resources-tensorflow-papers/
* TensorFlow exercises: https://github.com/Kyubyong/tensorflow-exercises
* TensorFlow workshops: https://github.com/tensorflow/workshops
* DL Applied Project #1: Food Classification with TensorFlow & Keras: http://blog.stratospark.com/deep-learning-applied-food-classification-deep-learning-keras.html#Loading-and-Preprocessing-Dataset

#### Keras

* Stateful LSTM in Keras: https://philipperemy.github.io/keras-stateful-lstm/

#### PyTorch

* Learning PyTorch with examples: http://pytorch.org/tutorials/beginner/pytorch_with_examples.html#warm-up-numpy
* PyTorch tutorials github: https://github.com/yunjey/pytorch-tutorial
* PyTorch tutorial distilled: https://towardsdatascience.com/pytorch-tutorial-distilled-95ce8781a89c
* Practical PyTorch: https://github.com/Kyubyong/practical-pytorch
* PyTorch exercises: https://github.com/Kyubyong/pytorch_exercises
* Kind PyTorch Tutorial: https://github.com/GunhoChoi/Kind-PyTorch-Tutorial

#### MXNet

* Keras with MXNet backend: https://github.com/deep-learning-tools/keras/wiki/Installation-Guide---Keras-with-MXNet-backend
* MXNet notebooks: https://github.com/dmlc/mxnet-notebooks

#### scikit-cuda

* Documentation: http://scikit-cuda.readthedocs.io/en/latest/reference.html#library-wrapper-routines

#### OpenAIgym

* Getting CUDA 8 to Work With openAI Gym on AWS and Compiling Tensorflow for CUDA 8 Compatibility: https://davidsanwald.github.io/2016/11/13/building-tensorflow-with-gpu-support.html

#### PyMC3

* Official Youtube playlist: https://www.youtube.com/playlist?list=PL1Ma_1DBbE82OVW8Fz_6Ts1oOeyOAiovy

#### Pyro (Uber, built on PyTorch)

* Home: http://pyro.ai/
* Examples and tutorials: http://pyro.ai/examples/
* Documentation: https://pythonhosted.org/Pyro4/index.html
* Documentation: http://docs.pyro.ai/en/0.1.2-release/
* Documentation: http://pyro.ai/examples/intro_part_i.html
(I have no idea why the docs are all over the place)

#### ONNX: Open Network Neural Exchange (Facebook + Microsoft)

* Repo: https://github.com/onnx
* ONNX tensorflow: https://github.com/onnx/tensorflow-onnx
* ONNX mxnet: https://github.com/onnx/onnx-mxnet
* Tutorials: https://github.com/onnx/tutorials
* FB blog: https://research.fb.com/facebook-and-microsoft-introduce-new-open-ecosystem-for-interchangeable-ai-frameworks/

#### Apache Spark

* GPU Acceleration on Apache Spark: http://www.spark.tc/gpu-acceleration-on-apache-spark-2/

#### CNTK:

* Model Gallery (examples etc.): https://www.microsoft.com/en-us/cognitive-toolkit/features/model-gallery/?filter=Tutorial,Python
* CNTK repo Tutorials: https://github.com/Microsoft/CNTK/tree/master/Tutorials

### Specific topic based resources

#### Python

* Deep Learning with Python: https://github.com/Apress/deep-learning-w-python

#### Optimization related:

* Adam-vs-SGD Numpy: https://github.com/jrios6/Adam-vs-SGD-Numpy
* Stochastic Gradient Descent (SGD) with Python: https://www.pyimagesearch.com/2016/10/17/stochastic-gradient-descent-sgd-with-python/
* Ridge & Lasso Regression in Python: https://www.analyticsvidhya.com/blog/2016/01/complete-tutorial-ridge-lasso-regression-python/
* The concept of Conjugate Gradient Descent in Python: http://ikuz.eu/2015/04/15/the-concept-of-conjugate-gradient-descent-in-python/

#### Sequential Models/ RNN-LSTM-GRU etc. related

* Learning Math with LSTM and Keras: http://cpury.github.io/learning-math/
* Vanilla LSTM with Numpy: http://blog.varunajayasiri.com/numpy_lstm.html

#### Sentiment Analysis

* Twitter Sentiment Analysis using combined LSTM-CNN Models: http://konukoii.com/blog/2018/02/19/twitter-sentiment-analysis-using-combined-lstm-cnn-models/

#### Data Mining related:

##### Real Estate:

* Real estate valuation usng data mining software: https://ac.els-cdn.com/S1877705816339625/1-s2.0-S1877705816339625-main.pdf?_tid=a6392af8-e513-4fb5-aa7d-52e3e1415580&acdnat=1521846137_c6f9bfcf206d1ac88318fe8579b56cc6
* Predicting Home Prices from Realty Descriptions: https://www.christianpeccei.com/homeprice/
* Predicting RE Price using Text Mining: http://arno.uvt.nl/show.cgi?fid=134740

#### Natural Language Processing

* 5 Fantastic NLP Resources: http://houseofbots.com/news-detail/2328-4-5-fantastic-practical-natural-language-processing-resources
* Finding parts of speech using python (spacey): https://www.oreilly.com/learning/how-do-you-find-the-parts-of-speech-in-a-sentence-using-python

#### Transfer Learning

* Transfer Learning: Machine Learning's Next Frontier: http://ruder.io/transfer-learning/index.html

#### Data Augmentation:

* Article includes info on data augmentation in TensorFlow: https://www.tensorflow.org/tutorials/deep_cnn#convolutional-neural-networks
* On-the-fly Data Augmentation for above tut starts here on github: https://github.com/tensorflow/models/blob/master/tutorials/image/cifar10/cifar10_input.py#L171

#### Finance, Trading, Time-Series related

* Intro to learning to trade with Reinforcement Learning: http://www.wildml.com/2018/02/introduction-to-learning-to-trade-with-reinforcement-learning/?lipi=urn%3Ali%3Apage%3Ad_flagship3_feed%3BHVokF2EaRxKqj8erYR%2Fizg%3D%3D
* Schmidhuber et al - Neural Nets in Finance: http://people.idsia.ch/~juergen/finance.html
* Neural Nets for Algo Trading: https://medium.com/machine-learning-world/neural-networks-for-algorithmic-trading-2-1-multivariate-time-series-ab016ce70f57
* Neural Nets for algo trading - time series forecasting - https://medium.com/machine-learning-world/neural-networks-for-algorithmic-trading-part-one-simple-time-series-forecasting-f992daa1045a
* Neural Decomposition of Time-Series Data for Effective Generalization: https://arxiv.org/abs/1705.09137v2
* Deep Learning in Finance - Learning to trade with Q-RL and DQNS (Reinforcement Learning): https://chatbotslife.com/deep-learning-in-finance-learning-to-trade-with-q-rl-and-dqns-6c6cff4a1429
* Deep Learning models in Finance: https://sinews.siam.org/Details-Page/deep-learning-models-in-finance-2