Deep Learning Hub

Tomorrow Tue 4/3 talk on "Deep Learning & its application in Medicine" at 456 W. Olive Avenue, Sunnyvale. This is a free event & no pre-registration is required. Walk-ins are welcome. Come for talk, stay to network @machinelearnbot @MachineLearnDC @DeepLearningHub @deeplearning4j

Deadline to apply for postdoc position in deep continual learning is coming up tomorrow. @slashML @women_in_ai @wimlds @DeepLearningHub twitter.com/risi1979/statu…

@yoavgo @nlpmattg @seb_ruder @Smerity @dennybritz A good example of a paper that pulls together quite a few useful techniques is: openreview.net/forum?id=S1NHa… . CIFAR 10 SoTA, which is an interesting dataset IMO since it is quite small, so needs good augmentation, regularization, architecture, etc

[1801.01586] A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines arxiv.org/abs/1801.01586 This looks like a very useful survey/tutorial paper.

Wrote a blog post on implementing a PyTorch-like autodifferentiation library (in @rustlang): @maciejkula/building-an-autodifferentiation-library-9ccf32c7a658" target="_blank" rel="nofollow noopener">medium.com/@maciejkula/bu…

Introduction to Linguistics for Natural Language Processing - cl.cam.ac.uk/teaching/1314/… #NLProc #Linguistics

The ML research community has long been driven by the need to publish, which results in a stark, sometimes ridiculous bias towards complexity. Remember to ask: "can we do this with k-means and logistic regression?"

One thing I realize people don't like: Being told to think critically about a problem.People: AI algorithms are not magic. When you're first learning them, take some time to consider the knobs you're turning. It's amazing what applying the scientific method (step by step ) does.

How to unit test #machinelearning code . @keeper6928/how-to-unit-test-machine-learning-code-57cf6fd81765?imm_mid=0f7a0a&cmp=em-data-na-na-newsltr_20171101" target="_blank" rel="nofollow noopener">medium.com/@keeper6928/ho…

A review of the top 5 papers ML arXiv papers of 2017 (according to the number of likes each paper's @BrundageBot tweet received):

New: My research w/@andyguess/@JasonReifler providing 1st behavioral estimates of fake news exposure in 2016 dartmouth.edu/~nyhan/fake-ne… Key findings: -heavily concentrated among w/most conservative info diets -Facebook key vector of exposure -fact-checks did not reach those exposed

Top 10 reasons #deeplearning isn’t getting us to artificial general intelligence. A critique of deep learning, 5 years into its resurgence, by @garymarcus arxiv.org/abs/1801.00631

“From Perceptron to Deep Neural Nets” by @adichrisb buff.ly/2DVAp3v

ICYMI... twitter.com/Reza_Zadeh/sta…

My publisher is doing a deal (today only) where you can get half off my book "Deep Learning with Python", as well as its R version, "Deep Learning with R" (co-authored with JJ Allaire) manning.com/dotd?a_aid=ker…

A reinforcement learning agent that learns to program new neural network architectures. Same/better results as LSTMs but with funky nonlinearities (sine, SeLus, etc) and new connections that result in different activation patterns😯 einstein.ai/research/domai… arxiv.org/abs/1712.07316

New results on word embeddings with FastText in this paper: arxiv.org/abs/1712.09405 fb.me/3qcGSgz3k

In depth discussion of neural nets for autonomous driving and visualization of layers - Byte magazine, 1989 twitter.com/ankurhandos/st…

wav2letter: end-to-end speech recognition engine from FAIR, now open source. fb.me/1KE0VqEtS

A nice summary... twitter.com/dennybritz/sta…