Posts Tagged ‘deeplearning’

google released variant calling with deep learning

December 16, 2017

$GOOG Is Giving Away AI That Can Build Your Genome Seq. https://Research.GoogleBlog.com/2017/12/deepvariant-highly-accurate-genomes.html + https://www.Wired.com/story/google-is-giving-away-ai-that-can-build-your-genome-sequence GATK creators now doing a tensor-flow version. Release sounded a bit like IBM unveiling Deep Blue decades ago: “Today, we announce…DeepVariant, a #DeepLearning tech…"

Steven Salzberg’s response to deep variant:
https://www.forbes.com/sites/stevensalzberg/2017/12/11/no-googles-new-ai-cant-build-your-genome-sequence/#5953db7b5774

QT:{{"On Monday, Google released a tool called DeepVariant that uses deep learning—the machine learning technique that now dominates AI—to identify all the mutations that an individual inherits from their parents.1 Modeled loosely on the networks of neurons in the human brain, these massive mathematical models have learned how to do things like identify faces posted to your Facebook news feed, transcribe your inane requests to Siri, and even fight internet trolls. And now, engineers at Google Brain and Verily (Alphabet’s life sciences spin-off) have taught one to take raw sequencing data and line up the billions of As, Ts, Cs, and Gs that make you you.”
"}}

Google Is Giving Away AI That Can Build Your Genome Sequence
https://www.wired.com/story/google-is-giving-away-ai-that-can-build-your-genome-sequence/

The Serial-Killer Detector | The New Yorker

December 9, 2017

The Serial-Killer Detector
https://www.NewYorker.com/magazine/2017/11/27/the-serial-killer-detector Journalist finds subtle yet predictive crime patterns with the computer. Wonder if #DeepLearning would be helpful here? Probably not // #CrimeMap

Qt:{{‘
A former journalist, equipped with an algorithm and the largest collection of murder records in the country, finds patterns in crime. “}}

New Theory Cracks Open the Black Box of Deep Learning | Quanta Magazine

November 12, 2017

New Theory Cracks Open the Black Box of #DeepLearning
https://www.QuantaMagazine.org/new-theory-cracks-open-the-black-box-of-deep-learning-20170921/ Highlights the importance of a compression phase for generalization

QT:{{”
“Then learning switches to the compression phase. The network starts to shed information about the input data, keeping track of only the strongest features — those correlations that are most relevant to the output label. This happens because, in each iteration of stochastic gradient descent, more or less accidental correlations in the training data tell the network to do different things, dialing the strengths of its neural connections up and down in a random walk. This
randomization is effectively the same as compressing the system’s representation of the input data. As an example”
“}}

interactive cnn

June 18, 2017

an intuitive example of how CNN works

http://playground.tensorflow.org/

Journal Club Paper

June 18, 2017

Zhou, J. and Troyanskaya, O.G. (2015). Predicting effects of noncoding variants with deep learning–based sequence model. Nature Methods, 12, 931–934.

Predicting (& prioritizing) effects of noncoding variants w. [DeepSEA] #DeepLearning…model
https://www.Nature.com/nmeth/journal/v12/n10/full/nmeth.3547.html Trained w #ENCODE data

By sparring with AlphaGo, researchers are learning how an algorithm thinks

February 26, 2017

With #AlphaGo researchers are learning how an algorithm thinks
https://qz.com/897498/by-sparring-with-alphago-researchers-are-learning-how-an-algorithm-thinks What images #NNs conjure up for a classification term

QT:[{”
-“Tyka was part of the Google team that first published work on DeepDream, a computer-vision experiment that went viral in 2015. The team trained a deep neural network to classify images, i.e. show the network a picture, it tells you what the image depicts. Except instead of asking it to look at pictures, they programmed the network to look at a word and produce what it thought would be an image that represents the word. The deep neural network would then supply its visual “idea” of different words.

And it worked. The team gave the network the word “banana,” for example, and it produced a dizzying fractal of banana-shaped objects. But the experiment also provided insight into how the machine thought about objects. When asked to produce dumbbells, the network generated gray dumbbell shapes with beige protrusions—arms. The neural net correlated arms and dumbbells so highly that they were seen as almost one object.”

“}}

The Great A.I. Awakening – The New York Times

December 26, 2016

The Great AI Awakening
http://www.NYTimes.com/2016/12/14/magazine/the-great-ai-awakening.html Quick history of #DeepLearning & its dramatic success in translation. Is med. diagnosis next?

Now flattered to have had 2 Hinton alumni in my lab…!

Journal Club

July 23, 2016

Basset: #DeepLearning the regulatory code w/…NNs by @noncodarnia lab http://genome.cshlp.org/content/early/2016/05/03/gr.200535.115 Has score for all possible SNVs in the genome

“Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks”

A deep learning framework for modeling structural features of RNA-binding protein targets

July 12, 2016

#Deeplearning framework for modeling…RBP sites
http://nar.oxfordjournals.org/content/44/4/e32 Uses topic models & determines key primary & tert. struct. features

http://nar.oxfordjournals.org/content/44/4/e32

Apple’s Deep Learning Curve

November 6, 2015

$AAPL’s #DeepLearning Curve
http://www.bloomberg.com/news/articles/2015-10-29/apple-s-secrecy-hurts-its-ai-software-development A very secretive culture controlling Siri & your phone