Friday, December 20, 2013

#NIPS2013 sweet aftertastes

So NIPS2013 is finished, let's see what was interesting and picked by others:

Blog coverage:

I also found these links of interest

As well as well as these tweets and their interesting links suggested on the #NIPS2013 tag on twitter (here is google docs list of all the tweets):

Animesh Garg ‏@Animesh_Garg

Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics ProgramsVikash K. Mansinghka, Tejas D. Kulkarni, Yura N. Perov, Joshua B. Tenenbaum

Il Memming Park ‏@memming
A simple example of Dirichlet process mixture inconsistency for the number of components[PDF]

Suvash Sedhain ‏@suvsh
Deep content based recommendation #NIPS2013 … and my answer in Quora

brendan o'connor ‏@brendan64
since i keep telling people at #nips2013 about @redpony's notes on adagrad, here they are, they are handy => …

Notes on AdaGrad by Chris Dyer

Andreas Mueller ‏@t3kcit
Great tutorial by Rob Fergus on Deep Learning for Vision at #NIPS2013. Slides up soon, for now read their paper: …

brendan o'connor ‏@brendan64
#NIPS2013 I really love Pearl's 2009 review … I imagine this tutorial is hard to understand w/o reading that first ...

.@brendan642 #NIPS2013 
.. also good are Cosma Shalizi's book chapters: … … …

Shane Conway ‏@statalgo
"Approximate Dynamic Programming Finally Performs Well in the Game of Tetris" … #ADP #NIPS2013

Alexandre Passos ‏@atpassos_ml
New blog post: #NIPS2013 reading list …

Gilles Louppe ‏@glouppe
My step for #OpenScience: code+demo for our #NIPS2013 paper "Understanding variable importances in random forests" …

Animesh Garg ‏@Animesh_Garg
Distributed Submodular Maximization: Simple effective and very few assumptions on functions win-win #NIPS2013

Richard ‏@RichardSocher

Demo of our website to make machine learning for text classification easily accessible: at #NIPS2013

Gilles Louppe ‏@glouppe

Just presented "Scikit-Learn: Machine Learning in the Python ecosystem" at MLOSS #NIPS2013 Find the notebook at …

Andreas Mueller ‏@t3kcit
ClowdFlows looks like a great way to design data pipelines and do interactive exploration via the web #NIPS2013

Olivier Grisel ‏@ogrisel

Decision Jungles: memory efficient alternative to randomized trees … /cc @glouppe @pprett via @Chris_Said #NIPS2013

Andreas Mueller ‏@t3kcit

As a consequence of #NIPS2013 I'm finally installing pylearn2 … Probably the best way to get started with deep learning

Chandra ‏@sekhardrona

Deep learning algorithms could make smart drugs via @physorg_com #NIPS2013 #MachineLearning

Dave Sullivan ‏@_DaveSullivan

FastML: 13 #NIPS2013 papers that caught our eye …

Dirk Gorissen ‏@elazungu

Interesting paper from #NIPS2013 "able to predict >95% of the weights of a deep NN without any drop in accuracy" …

Adam Stankiewicz ‏@astankiew

NIPS 2013 Workshop on Data Driven Education … #nips2013 via @jonathanhuang11

eliana feasley ‏@eli_awry

Announced KA data sharing plans at #NIPS2013 . We're working on a whitepaper with more details, but initial info at

Chandra ‏@sekhardrona

explain my data: NIPS and the Zuckerberg Visit #NIPS2013 #DeepLearning

Michael Witbrock ‏@witbrock
My latest : Cyc and Semantic Construction Grammar #NIPS2013… on @slideshare … via @SlideShare

Tim van Erven ‏@tverven

Blog post: Wrote a PAC-Bayes mini-tutorial on the plane to #NIPS2013 to relate to standard concentration inequalities …
joseph reisinger ‏@josephreisinger
"Machine learning is a complex ecosystem"— Max Welling on the whole "Zuck at #nips2013" thing …

Erin LeDell ‏@ledell
Now anyone that can query a database can do Bayesian inference … #BayesDB
Dropout (neural networks/Geoffrey Hinton) as adaptive regularization in GLMs #NIPS2013 …

Erin LeDell ‏@ledel
Compressive feature learning can reduce text feature space by two orders of magnitude compared to k-grams #NIPS2013 …

No comments: