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

Starlink Mini offers fast, reliable internet on the go—great for traveling, camping, exploring, boating, RVing, and more. Stay connected without dead zones or slow speeds. Order online in under 2 minutes.

@yoavgo @nlpmattg @seb_ruder @Smerity @dennybritz A good example of a paper that pulls together quite a few useful techniques is: https://t.co/1t0SxbZZBr . 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 https://t.co/hslgKh00Bh This looks like a very useful survey/tutorial paper.

Wrote a blog post on implementing a PyTorch-like autodifferentiation library (in @rustlang):

Introduction to Linguistics for Natural Language Processing - https://t.co/LHrlu3LgMc #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 .

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 https://t.co/dRI5P6NN04 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

“From Perceptron to Deep Neural Nets” by @adichrisb

ICYMI...

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)

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😯 https://t.co/WPLEJgT0pO https://t.co/UEqgpBuG14

New results on word embeddings with FastText in this paper: https://t.co/MePzbgOcM0

In depth discussion of neural nets for autonomous driving and visualization of layers - Byte magazine, 1989

wav2letter: end-to-end speech recognition engine from FAIR, now open source.

A nice summary...