Citizen Science Salon is a partnership between Discover and SciStarter.org. In 2016, a team of Alzheimer's disease researchers at Cornell University hit a dead end. The scientists were studying mice, looking for links between Alzheimer's and blood flow changes in the brain. For years, scientists have known that reduced blood flow in the brain is a symptom of Alzheimer's disease. More recent research has also shown that this reduced blood flow can be caused by clogged blood vessels -- or "stalls." And by reversing these stalls in mice, scientists were able to restore their memory.

Traditionally, nonlinear inversion, direct inversion, or wave estimation methods have been used for reconstructing images from MRE displacement data. In this work, we propose a convolutional neural network architecture that can map MRE displacement data directly into elastograms, circumventing the costly and computationally intensive classical approaches. In addition to the mean squared error reconstruction objective, we also introduce a secondary loss inspired by the MRE mechanical models for training the neural network. Our network is demonstrated to be effective for generating MRE images that compare well with equivalents from the nonlinear inversion method.

We present hidden fluid mechanics (HFM), a physics informed deep learning framework capable of encoding an important class of physical laws governing fluid motions, namely the Navier-Stokes equations. In particular, we seek to leverage the underlying conservation laws (i.e., for mass, momentum, and energy) to infer hidden quantities of interest such as velocity and pressure fields merely from spatio-temporal visualizations of a passive scaler (e.g., dye or smoke), transported in arbitrarily complex domains (e.g., in human arteries or brain aneurysms). Our approach towards solving the aforementioned data assimilation problem is unique as we design an algorithm that is agnostic to the geometry or the initial and boundary conditions. This makes HFM highly flexible in choosing the spatio-temporal domain of interest for data acquisition as well as subsequent training and predictions. Consequently, the predictions made by HFM are among those cases where a pure machine learning strategy or a mere scientific computing approach simply cannot reproduce. The proposed algorithm achieves accurate predictions of the pressure and velocity fields in both two and three dimensional flows for several benchmark problems motivated by real-world applications. Our results demonstrate that this relatively simple methodology can be used in physical and biomedical problems to extract valuable quantitative information (e.g., lift and drag forces or wall shear stresses in arteries) for which direct measurements may not be possible.

Journal of Parallel and Distributed Computing 104, 19-35.

We have constructed an information extraction system called the Mars Target Encyclopedia that takes in planetary science publications and extracts scientific knowledge about target compositions. The extracted knowledge is stored in a searchable database that can greatly accelerate the ability of scientists to compare new discoveries with what is already known. To date, we have applied this system to ~6000 documents and achieved 41-56% precision in the extracted information.

Transcranial direct current stimulation has been claimed to enhance learning.Credit: Liz Hafalia/Polaris/eyevine Is there a common element that binds diverse mental abilities, from language to mental arithmetic? Or do these skills compete for our brains' limited resources? In The Genius Within, Dav...

Building off of work published in 2015, the team used AI to analyze the speech patterns of 59 individuals who had participated in a separate study. Transcripts of an interview the participants took part in were broken down into parts of speech and were scored on how coherent the sentences were. Then, the machine learning model determined, based on those speech patterns, who was at risk of developing psychosis and who wasn't. Of those participants, 19 developed a psychotic disorder within two years while 40 did not and the model was able to predict that with 83 percent accuracy. It was also able to differentiate speech patterns of patients who had recently developed psychosis from those of healthy patients with 72 percent accuracy.

Building off of work published in 2015, the team used AI to analyze the speech patterns of 59 individuals who had participated in a separate study. Transcripts of an interview the participants took part in were broken down into parts of speech and were scored on how coherent the sentences were. Then, the machine learning model determined, based on those speech patterns, who was at risk of developing psychosis and who wasn't. Of those participants, 19 developed a psychotic disorder within two years while 40 did not and the model was able to predict that with 83 percent accuracy. It was also able to differentiate speech patterns of patients who had recently developed psychosis from those of healthy patients with 72 percent accuracy.

We present a selection of four articles describing deployed applications plus two more articles that discuss work on emerging applications. Since then, we have seen examples of AI applied to domains as varied as medicine, education, manufacturing, transportation, user modeling, and citizen science. The 2014 conference continued the tradition with a selection of 7 deployed applications describing systems in use by their intended end users, and 14 emerging applications describing works in progress. This year's special issue on innovative applications features articles describing four deployed and two emerging applications. The articles include three different types of recommender systems, which may be as much of a critique of the role of technology in society as it is an indication of recent research trends.

A company called Zebra Medical Vision (Zebra-Med) has unveiled a new service called Zebra AI1 that uses algorithms to examine your medical scans for a dollar each. The deep learning engine can examine CT, MRI and other scans and automatically detect lung, liver, heart and bone diseases. New capabilities like lung and breast cancer, brain trauma, hypertension and others are "constantly being released," the company says. The results are then passed on to radiologists, saving them time in making a diagnosis or requesting further tests. Engadget met Zebra-Med CEO and co-founder Elad Benjamin at the Hello Tomorrow startup conference in Paris, where he delivered the news about the scans.