Search

Data-sampling method makes “sketches” of unwieldy biological datasets while still capturing the full diversity of cell types.

Could a machine do better?

We are entering an era of AI-Mediated Communication (AI-MC) where interpersonal communication is not only mediated by technology, but is optimized, augmented, or generated by artificial intelligence. Our study takes a first look at the potential impact of AI-MC on online self-presentation. In three...

ProductNet is a collection of high-quality product datasets for better product understanding. Motivated by ImageNet, ProductNet aims at supporting product representation learning by curating product datasets of high quality with properly chosen taxonomy. In this paper, the two goals of building high...

If you have an ASP.NET / ASP.NET Core, .NET web services, .NET Microservices, or any other .NET server application and are considering the use of Redis then please take a look at NCache as it is an ideal Redis alternative for .NET applications.

Study shows that artificial neural networks can be used to drive brain activity.

MIT/MGH's image-based deep learning model can predict breast cancer up to five years in advance.

MIT CSAIL project shows the neural nets we typically train contain smaller “subnetworks” that can learn just as well, and often faster.

Rapidly advancing technologies, including artificial intelligence, robotics, 3D-printing, smart-phones, smart-homes, precision medicine and diagnostics, promise to disrupt health care as we know it.

Natural language is hierarchically structured: smaller units (e.g., phrases) are nested within larger units (e.g., clauses). When a larger constituent ends, all of the smaller constituents that are nested within it must also be closed. While the standard LSTM architecture allows different neurons to...

Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary experience is that the sparse architectures produced by pruning...

The past several years have seen enormous growth of research papers in machine learning and deep learning. For a while now, I’ve been curious about the trends of this growth. For example, what papers have had an especially significant impact on the community? What are topics that researchers are…

Vision science, particularly machine vision, has been revolutionized by introducing large-scale image datasets and statistical learning approaches. Yet, human neuroimaging studies of visual perception still rely on small numbers of images (around 100) due to time-constrained experimental procedures...

Visual blends are an advanced graphic design technique to draw attention to a message. They combine two objects in a way that is novel and useful in conveying a message symbolically. This paper presents VisiBlends, a flexible workflow for creating visual blends that follows the iterative design...

We developed a deep learning model that uses full-field mammograms and traditional risk factors, and found that our model was more accurate than the Tyrer-Cusick model (version 8), a current clinical standard.
Key Points:
A deep learning (DL) mammography-based model identified women at high risk for...

Algorithm stitches multiple datasets into a single “panorama,” which could provide new insights for medical and biological studies.

In some cases, radio frequency signals may be more useful for caregivers than cameras or other data-collection methods.

New method quickly detects instances when neural networks make mistakes they shouldn’t.

Google’s homepage on Feb. 1, 2019, celebrated Sojourner Truth. But its algorithms do not reflect the same inclusive approach.

AI develops human-like number sense – taking us a step closer to building machines with general intelligence