AI and Brain Link Roundup – Week 16.5

This is a ~weekly Link Roundup of the most interesting content I found in the past week.

News and Resources for Artificial Intelligence, Neuroscience.


Towards deep learning with segregated dendritesarxiv.org

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the brain optimizes cost functions.


Brain circuit enables split-second decisions when cues conflict | MIT Newsnews.mit.edu

mit researchers have identified a circuit in the brain that is critical for governing how we respond to conflicting environmental cues.


Neural ensemble dynamics underlying a long-term associative memorynature.com

The brain’s ability to associate different stimuli is vital for long-term memory, but how neural ensembles encode associative memories is unknown. Preliminary neurobiological evidence that a supervised learning model shapes neural population activity.


Deep Learning and the Stock Market – DZone Big Datadzone.com

learn how a new research study says that artificial intelligence affects capital market data and how deep learning is overcoming the efficient market.


Toward an Integration of Deep Learning and Neuroscience – journal.frontiersin.org

Neuroscience has focused on the detailed implementation of computation, studying neural codes, dynamics and circuits. In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively uniform initial architectures. Two recent developments have emerged within machine learning that create an opportunity to connect these seemingly divergent perspectives.


Machine Learning Using Support Vector Machines | R-bloggerswww.r-bloggers.com

support vector machines (svm) is a data classification method that separates data using hyperplanes. the concept of svm is very intuitive and …


IBM’s ‘Rodent Brain’ Chip Could Make Our Phones Hyper-Smart | WIREDwww.wired.com

for the first time, ibm is sharing its brain-like microprocessor with the outside world.


Rodeorodeo.yhat.com

Rodeo is an integrated environment for python-based data science. It’s Rstudio for Python.


U of T researcher launches startup to help find new smart drugswww.utoronto.ca

Igor Stagljar likens the process of commercializing his ground-breaking research into cell membrane proteins – which has yielded hundreds of new targets for drug-makers seeking cures for cancer and other deadly diseases – to building a highly automated tesla factory.

 

Leonardo Restivo

Behavioral Neuroscientist , M.Sc., Ph.D. - Passionate about Behavior, Data Visualization & Psychology. Read my CV+résumé. Follow me on twitter @scipleneuro