ArtificialIntelligenceArticles
2.96K subscribers
1.64K photos
9 videos
5 files
3.86K links
for who have a passion for -
1. #ArtificialIntelligence
2. Machine Learning
3. Deep Learning
4. #DataScience
5. #Neuroscience

6. #ResearchPapers

7. Related Courses and Ebooks
Download Telegram
Functional brain network architecture supporting the learning of social networks in humans @ArtificialIntelligenceArticles
Tompson et al.: https://psyarxiv.com/r46gj/
#brainnetworks #neuroscience #socialnetworks #neuralnetworks @ArtificialIntelligenceArticles
Machine learning and complex biological data

By Chunming Xu and Scott A. Jackson

Machine learning has demonstrated potential in analyzing large, complex biological data. In practice, however, biological information is required in addition to machine learning for successful application.
https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1689-0
#artificialintelligence #machinelearning #deeplearning #biology #genomics
Toshiba's breakthrough algorithm realizes world's fastest, largest-scale combinatorial optimization

Toshiba Corporation has realized a major breakthrough in combinatorial optimization—the selection of the best solutions from among an enormous number of combinatorial patterns—with the development of an algorithm that delivers the world's fastest and largest-scale performance, and an approximately 10-fold improvement over current methods. Toshiba's new method can be applied to such daunting but essential tasks as identifying efficient delivery routes, determining the most effective molecular structures to investigate in new drug development, and building portfolios of profitable financial products.
https://m.phys.org/news/2019-04-toshiba-breakthrough-algorithm-world-fastest.html

#optimization #algorithms #computing
Causal Inference in Machine Learning

Ricardo Silva
Department of Statistical Science andCentre for Computational Statistics and Machine Learning
Imperial College

https://www.homepages.ucl.ac.uk/~ucgtrbd/talks/imperial_causality.pdf
Fooling automated surveillance cameras: adversarial patches to attack person detection
https://arxiv.org/pdf/1904.08653.pdf
Registration is still open to attend our Industrial Short Course on Deep Learning on May 16 - 17, 2019!

This 2-day course is primarily aimed at participants from industry and government agencies. The course will be given by Professor Xavier Bresson from the Nanyang Technological University (NTU) in Singapore, who is a leading researcher in the field of deep learning. Participants will learn about the theory of deep learning techniques as well as practical exercises. To register and learn more, visit the course webpage.

https://www.ipam.ucla.edu/programs/special-events-and-conferences/an-industrial-short-course-on-deep-learning-and-the-latest-ai-algorithms-2019/ #DeepLearning #Math #AI #NeuralNetworks
Brain signals translated into speech using artificial intelligence
#AI #deeplearning #recurrentneuralnetworks

A prosthetic voice decodes what the brain intends to say and generates (mostly) understandable speech, no muscle movement needed.

Many people who have lost the ability to speak communicate using technology that requires them to make tiny movements to control a cursor that selects letters or words on a screen. UK physicist Stephen Hawking, who had motor-neuron disease, was one famous example. He used a speech-generating device activated by a muscle in his cheek.

Because people who use such devices must type out words letter by letter, these devices can be very slow, producing up to ten words per minute. Natural spoken speech averages 150 words per minute. It’s the efficiency of the vocal tract that allows us to do that. So researchers decided to model the vocal system when constructing their decoder.

https://m.medicalxpress.com/news/2019-04-synthetic-speech-brain.html?fbclid=IwAR34iEZXpRhKpxQFuI6CLSTj981ugzwYRcPDUIhXx6BBsJ96p3Te58T2La0
https://newsroom.gehealthcare.com/ai-helps-doctors-critical-measurement-during-pregnancy/


Automating the process of measuring the fetal brain may help get crucial data faster and easier. However, measuring the fetal brain is not an easy task and requires a significant amount of manual input from the sonographer. Today, an artificial intelligence (AI) powered tool can make this process much easier.
A simple model of a neuron can be approximated by "deep network" with one hidden layer

A more detailed model of a neuron with NMDA (glutamate receptor) synapses requires SEVEN hidden layers https://www.biorxiv.org/content/10.1101/613141v1