sandy4321 / lists-1

things I think I should do, maybe

Things to read

• http://geocalc.clas.asu.edu/pdf/OerstedMedalLecture.pdf Oersted Medal Lecture 2002: Reforming the Mathematical Language of Physics

• http://www.cs.virginia.edu/~robins/YouAndYourResearch.html

• http://goodfeli.github.io/dlbook/

• http://cs.stanford.edu/people/karpathy/deepimagesent/

• http://benanne.github.io/2014/08/05/spotify-cnns.html

• http://erikbern.com/2013/12/20/more-insight-into-recommender-algorithms/

• https://cs231n.github.io/convolutional-networks/

• Carlson's mapper http://danifold.net/mapper/introduction.html

• Adam optimization: http://arxiv.org/abs/1412.6980 used by clickbait

• http://soumith.ch/eyescream/

• Jenn's newer paper: http://ebiquity.umbc.edu/paper/html/id/714/Topic-Modeling-for-RDF-Graphs

• http://www.amazon.com/Tools-Thought-History-Mind-Expanding-Technology/dp/0262681153 rec by @fogus

• possibly cool? http://multithreaded.stitchfix.com/blog/2015/09/17/deep-style/

• http://www.johndcook.com/blog/2015/09/15/nicholas-higham-on-mathematics-in-color/

• http://www.wildml.com/2015/09/implementing-a-neural-network-from-scratch/

• from Jen: http://arxiv.org/pdf/1406.1078.pdf

• from Eric: http://slides.skien.cc/hack-the-derivative-pygotham.pdf Analytic solution to the derivative for real valued functions / The definition of the function occurs on slide 74.

• https://mappingbabel.wordpress.com/2015/08/30/why-deep-learning-will-lead-to-new-troublesome-art/

• http://www.technologyreview.com/view/541276/deep-learning-machine-teaches-itself-chess-in-72-hours-plays-at-international-master/

• http://www.perceptualedge.com/articles/visual_business_intelligence/a_course_of_study_in_analytical_thinking.pdf

• http://www.datacommunitydc.org/blog/2015/6/predicting-topics-and-sharing-in-social-media (John's thing)

• http://www.economist.com/news/science-and-technology/21664943-computers-can-recognise-complication-diabetes-can-lead-blindness-now

• http://blog.kaggle.com/2015/09/16/icdm-winners-interview-3rd-place-roberto-diaz/

• http://blog.kaggle.com/2015/09/09/diabetic-retinopathy-winners-interview-1st-place-ben-graham/

and this uses pymc? http://blog.dominodatalab.com/ab-testing-with-hierarchical-models-in-python/

http://colah.github.io/posts/2014-07-NLP-RNNs-Representations/ etc.

• http://colah.github.io/archive.html
• http://cs.stanford.edu/people/karpathy/convnetjs//demo/classify2d.html
• http://colah.github.io/posts/2014-07-Conv-Nets-Modular/

http://coding-geek.com/how-databases-work/

read every word: http://benanne.github.io/

printing: http://www.cs.toronto.edu/~fritz/absps/transauto6.pdf (transforming autoencoders)

Retrospective Event Detection in News http://data.betaworks.com/retrospective-event-detection/

FIRST STEPS IN DATA SCIENCE: AUTHOR-AWARE SENTIMENT ANALYSIS http://yanirseroussi.com/2015/05/02/first-steps-in-data-science-author-aware-sentiment-analysis/

A Word is Worth a Thousand Vectors http://multithreaded.stitchfix.com/blog/2015/03/11/word-is-worth-a-thousand-vectors/

is this any good? http://neuralnetworksanddeeplearning.com/

read a paper here! http://rtw.ml.cmu.edu/rtw/publications (NELL: Read The Web)

Do/read: https://github.com/google/deepdream Work through/replicate?

http://www.huffingtonpost.com/2014/03/18/facebook-deepface-facial-recognition_n_4985925.html

deep learning for java? http://deeplearning4j.org/eigenvector

http://sballas8.github.io/2015/08/11/Poet-RNN.html

Dataphoric: Split Testing for Geniuses http://www.dataphoric.com/split-testing-for-geniuses/

FBP inspired data flow syntax: The missing piece for the success of functional programming? http://bionics.it/posts/fbp-data-flow-syntax

https://usopendata.org/2015/07/29/dat-beta/

Modern Methods for Sentiment Analysis https://districtdatalabs.silvrback.com/modern-methods-for-sentiment-analysis

http://jvns.ca/blog/2014/11/27/ld-preload-is-super-fun-and-easy/

Why were these in a to-do?

• https://www.interviewcake.com/article/big-o-notation-time-and-space-complexity
• http://www.bloomberg.com/news/articles/2015-05-20/the-10-hedge-fund-supercomputer-that-s-sweeping-wall-street

http://www.pyimagesearch.com/2014/09/22/getting-started-deep-learning-python/

https://civisanalytics.com/blog/data-science/2015/08/13/scipy-2015-building-predictive-modeling-with-python/

http://www.janeriksolem.net/2009/01/pca-for-images-using-python.html

http://benanne.github.io/2015/03/17/plankton.html https://github.com/benanne/kaggle-ndsb

http://blog.kaggle.com/2015/07/27/taxi-trajectory-winners-interview-1st-place-team-%F0%9F%9A%95/

http://www.danielforsyth.me/mapping-nyc-taxi-data/

http://www.hexahedria.com/2015/08/03/composing-music-with-recurrent-neural-networks/

http://www.bzarg.com/p/how-a-kalman-filter-works-in-pictures/

http://www.alfredo.motta.name/cross-validation-done-wrong/

http://multithreaded.stitchfix.com/blog/2015/07/30/gam/

https://mitpress.mit.edu/books/little-prover

https://blog.sei.cmu.edu/post.cfm/field-study-technical-debt-208

https://timdettmers.wordpress.com/2015/07/27/brain-vs-deep-learning-singularity/

http://www.kdnuggets.com/2015/01/deep-learning-flaws-universal-machine-learning.html

read/do? https://nvidia.qwiklab.com/focuses/preview/102

http://www.researchgate.net/publication/227055046_Functional_Trees

http://ttic.uchicago.edu/~smale/papers/math_foundation_of_learning.pdf

Programming Computer Vision with Python http://programmingcomputervision.com/downloads/ProgrammingComputerVision_CCdraft.pdf

http://mlwave.com/kaggle-ensembling-guide/

Advanced R, from about "Function Factories" I think

https://github.com/justmarkham/DAT3/blob/master/code/14_nlp_class.py

http://nbviewer.ipython.org/github/podopie/DAT18NYC/blob/master/classes/13-expected_value_cost_benefit_analysis.ipynb

http://www.toptal.com/python/python-class-attributes-an-overly-thorough-guide

http://datascienceweekly.org/data-scientist-interviews/academia-to-metis-data-science-bootcamp-andy-martens-interview

Learning to Predict Rare Events in Categorical Time-Series Data http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.60.3908&rep=rep1&type=pdf

AUTOMATING TINDER WITH EIGENFACES http://crockpotveggies.com/2015/02/09/automating-tinder-with-eigenfaces.html

Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning https://timdettmers.wordpress.com/2014/08/14/which-gpu-for-deep-learning/

A Word is Worth a Thousand Vectors http://technology.stitchfix.com/blog/2015/03/11/word-is-worth-a-thousand-vectors/

Convolutional Neural Networks (LeNet) tutorial http://deeplearning.net/tutorial/lenet.html

read the diff sync paper: https://neil.fraser.name/writing/sync/

twitter users have better ideas? http://sloanreview.mit.edu/article/how-twitter-users-can-generate-better-ideas/

what is this python vw thing about http://nbviewer.ipython.org/github/hal3/vowpal_wabbit/blob/master/python/Learning_to_Search.ipynb

somebody said this was good? https://www.kaggle.com/c/word2vec-nlp-tutorial

http://blog.sashalaundy.com/blog/2014/12/05/the-best-lesson-from-hacker-school-is-hiding-in-plain-sight/

dplyr / pandas http://nbviewer.ipython.org/gist/TomAugspurger/6e052140eaa5fdb6e8c0

http://simplystatistics.org/2015/03/17/data-science-done-well-looks-easy-and-that-is-a-big-problem-for-data-scientists/

http://datascience.community/bootcamps

https://git-lfs.github.com/

http://en.wikipedia.org/wiki/Rubin_causal_model

Make A Lisp https://github.com/kanaka/mal/blob/master/process/guide.md

http://yet-another-data-blog.blogspot.com/

Conditional Random Fields

Four Assumptions Of Multiple Regression That Researchers Should Always Test http://www-psychology.concordia.ca/fac/kline/601/osborne.pdf

How do I become a data scientist? An evaluation of 3 alternatives (Laurie mentioned in her talk)

worth a damn? http://solutions-review.com/data-integration/top-terms-you-need-to-know-on-data-integration/

http://technocalifornia.blogspot.com/2014/12/ten-lessons-learned-from-building-real.html

Dirichlet Distribution in the Unit Simplex | NP//COMPLETE http://derekgossi.com/?p=311

ted dunning mapr als / free ebook IT'S ALREADY ON MY PHONE

on org mode: http://www.wisdomandwonder.com/