Computer Sciences news

Computer Sciences

Overcoming 'catastrophic forgetting': Algorithm inspired by brain allows neural networks to retain knowledge

Neural networks have a remarkable ability to learn specific tasks, such as identifying handwritten digits. However, these models often experience "catastrophic forgetting" when taught additional tasks: They can successfully ...

Computer Sciences

Can advanced AI can solve visual puzzles and perform abstract reasoning?

Artificial Intelligence has learned to master language, generate art, and even beat grandmasters at chess. But can it crack the code of abstract reasoning—those tricky visual puzzles that leave humans scratching their heads?

Computer Sciences

A new model for symbolic music generation using musical metadata

Artificial intelligence (AI) has opened new interesting opportunities for the music industry, for instance, enabling the development of tools that can automatically generate musical compositions or specific instrument tracks. ...

Computer Sciences

Bringing clarity to microscopic imaging: New tool removes motion artifacts

Imaging microscopic samples requires capturing multiple, sequential measurements, then using computational algorithms to reconstruct a single, high-resolution image. This process can work well when the sample is static, but ...

Hardware

New load balancing method enhances multiplayer game performance

Online gaming is increasingly popular. As such, server efficiency is becoming an increasingly urgent priority. With millions of players interacting in real-time, game servers are under enormous pressure to process a huge ...

Computer Sciences

Distinguishing real sounds from deepfakes

Deepfake videos generated by artificial intelligence grow increasingly difficult to identify as false, a challenge that could significantly skew the results of the upcoming presidential election.

Computer Sciences

Deep learning drives dynamic autofocus in grayscale images

Researchers from the Changchun Institute of Optics, Fine Mechanics and Physics of the Chinese Academy of Sciences have developed a novel autofocus method that harnesses the power of deep learning to dynamically select regions ...

Computer Sciences

New research could make weird AI images a thing of the past

Generative artificial intelligence (AI) has notoriously struggled to create consistent images, often getting details like fingers and facial symmetry wrong. Moreover, these models can completely fail when prompted to generate ...

Software

Quantum algorithm adopted by Google and IBM

An algorithm developed by Prakash Vedula, Ph.D., a professor at the University of Oklahoma School of Aerospace and Mechanical Engineering, has been incorporated into advanced computing software developed by Google and IBM. ...

Computer Sciences

Exploring the fundamental reasoning abilities of LLMs

Reasoning, the process through which human beings mentally process information to draw specific conclusions or solve problems, can be divided into two main categories. The first type of reasoning, known as deductive reasoning, ...

Computer Sciences

Google's GameNGen simulates parts of video game Doom

A team of researchers from Google Research, Google Deep Mind and Tel Aviv University reports that it is possible to use machine learning applications to recreate and simulate parts or all of an existing video game.

Computer Sciences

Universal accelerator finds faster answers to complex problems

A good machine-learning algorithm is a powerful research accelerator. Pair it with a computer simulation and it can sniff out mathematical shortcuts through the program, propelling scientists to faster insights about the ...

Computer Sciences

Without texts, automatic bug assignment still works well: Study

Automatic bug assignment has been well studied in the past decade. As textual bug reports usually describe the buggy phenomena and potential causes, engineers highly depend on these reports to fix bugs. Researchers heavily ...

Computer Sciences

New method allows AI to learn indefinitely

A team of AI researchers and computer scientists at the University of Alberta has found that current artificial networks used with deep-learning systems lose their ability to learn during extended training on new data. In ...