AI scientists can help neuroscientists develop mental health — MIT prof Sebastian Seung

Sebastian Seung

.

“There are definitely good opportunities for those with strong training in machine learning, who are excited by the idea of using artificial intelligence to create tools for neuroscientists,” Sebastian Seung, Howard Hughes Medical Institute investigator at MIT’s Department of Brain and Cognitive Sciences

.

Connectomics

Original: Helen Phillips NewScientist.com news service

.

“It has to be the biggest neural networking opportunity of the year, when the collective brains of the … Society for Neuroscience … gather for its annual meeting …

* * *

“The society’s president, David Van Essen … has selected some highlights of the conference that will be featured in a series of special lectures … such as neuroinformatics, neuroanatomy and neural computation have allowed progress that would have been inconceivable a decade ago.

* * *

Connectomics

Sebastian Seung studies neural networks using mathematical models and computer algorithms. Modeling a single neuron provides enough of a research challenge, but Seung is going a step further. One of the limitations in understanding how real brains work, he says, is the scarcity of information about how neurons are connected in the brain. An emerging field called ‘connectomics’ or computational neuroanatomy sets out to address this.

“New techniques, such as serial block-face scanning electron microscopy, are generating unprecedented amounts of data about the three-dimensional structure of brain circuitry at the nanometer scale.

“The computer will be an indispensable tool for analyzing and handling such data, and Seung’s lab has begun to develop algorithms, using some novel machine-learning techniques, to take raw images and generate data about structure and connectivity. That’s no mean feat, given that each tissue sample may contain 10,000 neurons and 10 million synapses – all of which need identifying and classifying. His group is also generating intriguing testable hypotheses about how synaptic plasticity and neuromodulators might be acting to create some of the anatomical and behavioral changes seen experimentally.

“As the field matures, it will aid the study of neural development, the process by which the brain wires itself up. ‘It could help us discover “connectopathies”- neuropathologies of connectivity that are associated with mental disorders,’ says Seung.

“The first classes in connectomics are being offered jointly at MIT and Harvard this fall. Seung, for one, hopes that it will inspire a new crop of computer scientists to begin working on the image analysis problems of connectomics. “There are definitely good opportunities for those with strong training in machine learning, who are excited by the idea of using artificial intelligence to create tools for neuroscientists,” he says.

Sebastian Seung is a Howard Hughes Medical Institute investigator at MIT’s Department of Brain and Cognitive Sciences.” . . . (full article)

Image Credit: MIT

+ + + + +

Newcomb’s commentary: “The mind, once expanded to the dimensions of larger ideas, never returns to its original size.” Oliver Wendell Holmes

Advertisements

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: