https://m.phys.org/news/2017-04-neural-networks.html#jCp
In the past 10 years, the best-performing artificial-intelligence systems—such as the speech recognizers on smartphones or Google’s latest automatic translator—have resulted from a technique called “deep learning.”
Most applications of deep learning use “convolutional” neural networks, in which the nodes of each layer are clustered, the clusters overlap, and each cluster feeds data to multiple nodes of the next layer.
3 Comments
Tomi Engdahl says:
How the brain recognizes faces: Machine-learning system spontaneously reproduces aspects of human neurology
December 1, 2016 by Larry Hardest
https://m.phys.org/news/2016-12-brain-machine-learning-spontaneously-aspects-human.html
Tomi Engdahl says:
How the brain recognizes faces: Machine-learning system spontaneously reproduces aspects of human neurology
https://m.phys.org/news/2016-12-brain-machine-learning-spontaneously-aspects-human.html
MIT researchers and their colleagues have developed a new computational model of the human brain’s face-recognition mechanism that seems to capture aspects of human neurology that previous models have missed.
Tomi Engdahl says:
Courts Are Using AI to Sentence Criminals. That Must Stop Now
https://www.wired.com/2017/04/courts-using-ai-sentence-criminals-must-stop-now/
Courts Are Using AI to Sentence Criminals. That Must Stop Now