Computer Sciences news

Computer Sciences

A model that can recognize speech in different languages from a speaker's lip movements

In recent years, deep learning techniques have achieved remarkable results in numerous language and image-processing tasks. This includes visual speech recognition (VSR), which entails identifying the content of speech solely ...

Nov 25, 2022

129

Computer Sciences

Making the most of quite little: Improving AI training for edge sensor time series

Engineers at the Tokyo Institute of Technology (Tokyo Tech) have demonstrated a simple computational approach for improving the way artificial intelligence classifiers, such as neural networks, can be trained based on limited ...

Nov 25, 2022

Mimicking human sleep as a way to prevent catastrophic forgetting in AI systems

A trio of researchers from the University of California, working with a colleague from the Institute of Computer Science of the Czech Academy of Sciences, has found that it is possible to prevent catastrophic forgetting in ...

Nov 24, 2022 report

0

123

New system can teach a group of cooperative or competitive AI agents to find an optimal long-term solution

Picture two teams squaring off on a football field. The players can cooperate to achieve an objective, and compete against other players with conflicting interests. That's how the game works.

Nov 23, 2022

0

74

A simpler path to better computer vision

Before a machine-learning model can complete a task, such as identifying cancer in medical images, the model must be trained. Training image classification models typically involves showing the model millions of example images ...

Nov 23, 2022

0

65

Computer Sciences

Meta team builds AI that plays 'Diplomacy' at very high level

A group of researchers on the Meta Fundamental AI Research Diplomacy Team (FAIR), affiliated with multiple institutions in the U.S., has added a negotiation component to its Diplomacy-playing AI system. In a paper published ...

Nov 23, 2022

Computer Sciences

How to put an end to gender biases in internet algorithms

Endless screeds have been penned on whether the internet algorithms with which we constantly interact suffer from gender bias, and all you need to do is carry out a simple search to see this for yourself.

Nov 23, 2022

An algorithm for optimal decision making under heavy-tailed noisy rewards

In data science, researchers typically deal with data that contain noisy observations. An important problem explored by data scientists in this context is the problem of sequential decision making. This is commonly known ...

Nov 22, 2022

Few-shot learning AI accurately 'senses' home appliances

NIALM (Non-Intrusive Appliance Load Monitoring) can "sense" appliances using electrical power. NIALM is used in homes and small buildings. For this, NIALM can require hundreds of labeled power signal images from each appliance ...

Nov 21, 2022

Researchers use 'complexity' as a guiding tool to make phase retrieval easier for coherent X-ray imaging

Since their discovery by Roentgen in 1895, X-rays have become an effective tool for doctors to take images of their patients' bones, organs and vessels, and make better diagnoses. Scientists have continued this quest to acquire ...

Nov 21, 2022

New tool enables comprehensive evaluation of datacenter performance

Datacenters are used by a myriad of companies, institutions and other operations, including large-scale online services such as e-commerce, search engines, online maps, social media, advertising and more. These datacenters ...

Nov 17, 2022

Empowering social media users to assess content helps fight misinformation

When fighting the spread of misinformation, social media platforms typically place most users in the passenger seat. Platforms often use machine-learning algorithms or human fact-checkers to flag false or misinforming content ...

Nov 16, 2022

New app creates time-lapse videos with a smartphone

An app developed by Cornell researchers uses augmented reality to help users repeatedly capture images from the same location with a phone or tablet to make time-lapse videos—without leaving a camera on site.

Nov 16, 2022

A promising optoelectronic synapse for reservoir computing based on alpha-indium selenide

Reservoir computing is an emerging computation framework based on the use of recurrent neural networks (i.e., networks in which data persists or reoccurs in patterns). This framework has the potential of reducing the time ...

Nov 15, 2022 feature

142

Solving brain dynamics gives rise to flexible machine-learning models

Last year, MIT researchers announced that they had built "liquid" neural networks, inspired by the brains of small species: a class of flexible, robust machine learning models that learn on the job and can adapt to changing ...

Nov 15, 2022

779

MemHC: An optimized GPU memory management framework for accelerating many-body correlation functions

Computers help physicists solve complicated calculations. But some of these calculations are so complex that a regular computer is not enough. In fact, some advanced calculations tax even the largest supercomputers. Now, ...

Nov 15, 2022

107

Researchers develop adaptive directional charging for efficient wireless rechargeable sensor networks

Smart factories, vehicles, and cities increasingly use wireless rechargeable sensor networks (WRSNs) for communication. A distinct advantage of WRSNs is that they can be placed in remote, inaccessible, or even biologically ...

Nov 15, 2022