deep learning tagged posts

New AI Sees Like a Human, Filling in the Blanks

How an AI Takes a Few Glimpses and Infers the Whole
A new AI agent developed by researchers at the University of Texas at Austin takes a few “glimpses” of its surroundings, representing less than 20 percent of the full 360 degree view, and infers the rest of the whole environment. What makes this system so effective is that it’s not just taking pictures in random directions but, after each glimpse, choosing the next shot that it predicts will add the most new information about the whole scene. Credit: David Steadman/Santhosh Ramakrishnan/University of Texas at Austin.

Computer scientists at The University of Texas at Austin have taught an artificial intelligence agent how to do something that usually only humans can do – take a few quick glimpses around and infer its whole environment, a skill necessary for the development o...

Read More

Face Recognition for Galaxies: Artificial Intelligence brings new tools to astronomy

A 'deep learning' algorithm trained on images from cosmological simulations is surprisingly successful at classifying real galaxies in Hubble images. Top row: High-resolution images from a computer simulation of a young galaxy going through three phases of evolution (before, during, and after the "blue nugget" phase). Middle row: The same images from the computer simulation of a young galaxy in three phases of evolution as it would appear if observed by the Hubble Space Telescope. Bottom row: Hubble Space Telescope images of distant young galaxies classified by a deep learning algorithm trained to recognize the three phases of galaxy evolution. The width of each image is approximately 100,000 light years. Credit: Image credits for top two rows: Greg Snyder, Space Telescope Science Institute, and Marc Huertas-Company, Paris Observatory. For bottom row: The HST images are from the Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS).

A ‘deep learning’ algorithm trained on images from cosmological simulations is surprisingly successful at classifying real galaxies in Hubble images. Top row: High-resolution images from a computer simulation of a young galaxy going through three phases of evolution (before, during, and after the “blue nugget” phase). Middle row: The same images from the computer simulation of a young galaxy in three phases of evolution as it would appear if observed by the Hubble Space Telescope. Bottom row: Hubble Space Telescope images of distant young galaxies classified by a deep learning algorithm trained to recognize the three phases of galaxy evolution. The width of each image is approximately 100,000 light years...

Read More

Deep Learning Transforms Smartphone Microscopes into Laboratory-grade devices

Image of a blood smear from a cell phone camera (left), following enhancement by the algorithm (center), and taken by a lab microscope (right). Credit: Ozcan Research Group/UCLA

Image of a blood smear from a cell phone camera (left), following enhancement by the algorithm (center), and taken by a lab microscope (right). Credit: Ozcan Research Group/UCLA

Researchers at the UCLA Samueli School of Engineering have demonstrated that deep learning, a powerful form of artificial intelligence, can discern and enhance microscopic details in photos taken by smartphones. The technique improves the resolution and color details of smartphone images so much that they approach the quality of images from laboratory-grade microscopes.

The advance could help bring high-quality medical diagnostics into resource-poor regions, where people otherwise do not have access to high-end diagnostic technologies...

Read More

Artificial Neural Networks Decode Brain Activity during performed and imagined Movements

In order to achieve better brain signal transmission quality, the researchers apply contact gel. Credit: Michael Veit

In order to achieve better brain signal transmission quality, the researchers apply contact gel. Credit: Michael Veit

Several groups from the Freiburg excellence cluster BrainLinks-BrainTools led by neuroscientist Dr. Tonio Ball are showing how ideas from computer science could revolutionize brain research. They illustrate how a self-learning algorithm decodes human brain signals that were measured by an electroencephalogram (EEG). It included performed movements, but also hand and foot movements that were merely thought of, or an imaginary rotation of objects...

Read More