Quick-Data-Science-Experiments-2018

To do

RPA (https://github.com/topics/rpa)
ML for cyber (https://github.com/wtsxDev/Machine-Learning-for-Cyber-Security)
CTR prediction for online learning (https://courses.cs.washington.edu/courses/cse599s/14sp/scribes/lecture20/lecture20_draft.pdf)
locally weighted bagging (https://maxhalford.github.io/blog/locally-weighted-bagging/)
Self-Supervised Visual Planning with Temporal Skip Connections (https://arxiv.org/pdf/1710.05268.pdf)
missing values pomogranaete (https://github.com/jmschrei/pomegranate/blob/master/tutorials/Tutorial_9_Missing_Values.ipynb)
Improving the Sensitivity of Online Controlled Experiments by Utilizing Pre-Experiment Data (http://www.exp-platform.com/Documents/2013-02-CUPED-ImprovingSensitivityOfControlledExperiments.pdf)
stacking and stacknet (http://blog.kaggle.com/2017/06/15/stacking-made-easy-an-introduction-to-stacknet-by-competitions-grandmaster-marios-michailidis-kazanova/)
how adversarial attacks work (https://blog.xix.ai/how-adversarial-attacks-work-87495b81da2d)
tacotron: end to end text to speech (https://arxiv.org/pdf/1703.10135.pdf)
Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks (https://arxiv.org/pdf/1701.01329.pdf)
try out seqgan (https://github.com/LantaoYu/SeqGAN)
RDKIT biotech (https://github.com/rdkit/rdkit-tutorials/tree/master/notebooks)
adversarial attack example (https://github.com/abhibhav14/adversarial-machine-learning)
Data Augmentation by Pairing Samples for Image Classification (https://arxiv.org/pdf/1801.02929.pdf)
try out pix2code (https://github.com/tonybeltramelli/pix2code)
Hypothesis tests for bernouille decisions (http://www.mdpi.com/1099-4300/19/12/696/htm)
try out RL tuner RNN + RL (https://github.com/tensorflow/magenta-demos/blob/master/jupyter-notebooks/RL_Tuner.ipynb)
ICML ML interpretability (http://people.csail.mit.edu/beenkim/papers/BeenK_FinaleDV_ICML2017_tutorial.pdf)
ICML Deep RL, Decision making (https://sites.google.com/view/icml17deeprl)
why not AUC (https://lukeoakdenrayner.wordpress.com/2018/01/07/the-philosophical-argument-for-using-roc-curves/)
WGAN math (https://lilianweng.github.io/lil-log/2017/08/20/from-GAN-to-WGAN.html)
Attention is all you need - Transformer(https://arxiv.org/pdf/1706.03762.pdf)
Expolatory factor analysis (https://www.let.rug.nl/nerbonne/teach/rema-stats-meth-seminar/Factor-Analysis-Kootstra-04.PDF)
fairness in ML (http://mrtz.org/nips17/#/)
Partially Observable MDP (https://www.cs.cmu.edu/~ggordon/780-fall07/lectures/POMDP_lecture.pdf)
AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine (http://www.aclweb.org/anthology/P17-2079)
https://databricks.com/blog/2017/04/26/processing-data-in-apache-kafka-with-structured-streaming-in-apache-spark-2-2.html
why I have lost faith in p-values (https://lucklab.ucdavis.edu/blog/2018/4/19/why-i-lost-faith-in-p-values)
Kubeflows (https://github.com/Azure/kubeflow-labs)

To do courses

cs231 stanford deep learning (http://cs231n.stanford.edu/slides/2016/)
Deep RL Bootcamp (https://sites.google.com/view/deep-rl-bootcamp/lectures)
probablistic graphical models (http://www.cs.cmu.edu/~epxing/Class/10708-17/lecture.html)

Done

generating music by fine tuning RNN with RL (https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/45871.pdf)
panopic segmentation (https://arxiv.org/pdf/1801.00868.pdf)
machine translation without the data (https://medium.com/@harshsayshi/machine-translation-without-the-data-21846fecc4c0)
On Calibration of Modern Neural Networks (https://arxiv.org/pdf/1706.04599.pdf)
Reducing the Variance of A/B Tests Using Prior Information (http://www.degeneratestate.org/posts/2018/Jan/04/reducing-the-variance-of-ab-test-using-prior-information/)
Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models (https://arxiv.org/pdf/1705.10843.pdf)
adversarial patch (sticker attacks) (https://arxiv.org/pdf/1712.09665.pdf)
Ranking and Calibrating Click-Attributed Purchases in Performance Display Advertising (https://drive.google.com/file/d/0BwF-hgLDpCD6UTlYLXBZX1BwWHc/view)
pix2code Generating code from GUI screenshot (https://arxiv.org/pdf/1705.07962.pdf)
hierarchical and interpretable skill acquisition in multi-task reinforcement learning (https://einstein.ai/static/images/pages/research/hierarchical-reinforcement-learning/iclr2018_HRL.pdf)
Learning meaningful location embeddings from unlabeled visits (http://www.sentiance.com/2018/01/29/learning-meaningful-location-embeddings-from-unlabeled-visits/)
Generating Wikipedia by Summarizing Long Sequences (https://arxiv.org/pdf/1801.10198.pdf)
shrinkage covariance (http://www.ledoit.net/honey.pdf)
skewed sample feedback loop
Intrinsically motivated self-aware agents (https://arxiv.org/pdf/1802.07442.pdf)
GAN mode collapse by sampling from latent space (https://www.exptechinc.com/2018/02/fighting-gan-mode-collapse-by-randomly-sampling-the-latent-space/)
Stochastic Hyperparameter Optimization through Hypernetworks (https://arxiv.org/pdf/1802.09419.pdf)
Multi Armed Bandits and Exploration Strategies (https://sudeepraja.github.io/Bandits/)
Variance networks (https://arxiv.org/pdf/1803.03764.pdf)
deep quantile network (https://towardsdatascience.com/deep-quantile-regression-c85481548b5a)
Explanation Methods in Deep Learning (https://arxiv.org/pdf/1803.07517.pdf)
deep learning and security (https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class12_security.ipynb)
Combining Powers of Two Predictors in Optimizing Real-Time Bidding Strategy under Constrained Budget (http://wnzhang.net/share/rtb-papers/two-pred-bid.pdf)
RUSBoost (http://sci2s.ugr.es/keel/pdf/algorithm/articulo/2010-IEEE%20TSMCpartA-RUSBoost%20A%20Hybrid%20Approach%20to%20Alleviating%20Class%20Imbalance.pdf)
kafka setup(https://community.cloudera.com/t5/Data-Ingestion-Integration/No-brokers-found-in-ZK/td-p/40952)
Duplex (https://ai.googleblog.com/2018/05/duplex-ai-system-for-natural-conversation.html)
Hierarchical Neural Story Generation (https://arxiv.org/pdf/1805.04833v1.pdf)