AI News by La Forge
Contact us

922 articles

'Liquid' machine-learning system adapts to changing conditions

2021-01-28 716

MIT researchers have developed a type of neural network that learns on the job, not just during its training phase. These flexible algorithms, dubbed "liquid" networks, change their underlying equations to continuously adapt ...
Tech Xplore - Machine learning drives NSynth Super's new sounds of music

2018-03-15 439

Look what Project Magenta people have been up to. After creating NSynth algorithm they have come up with a machine to serve as instrument, acting as the physical interface for the NSynth algorithm.
Evolvable neural units that can mimic the brain's synaptic plasticity

2021-01-14 433

Machine learning techniques are designed to mathematically emulate the functions and structure of neurons and neural networks in the brain. However, biological neurons are very complex, which makes artificially replicating ...
With little training, machine-learning algorithms can uncover hidden scientific knowledge

2019-07-03 423

Sure, computers can be used to play grandmaster-level chess (chess_computer), but can they make scientific discoveries? Researchers at the U.S. Department of Energy's Lawrence Berkeley National Laboratory (Berkeley Lab) have ...
System brings deep learning to Internet of Things devices

2020-11-13 415

Deep learning is everywhere. This branch of artificial intelligence curates your social media and serves your Google search results. Soon, deep learning could also check your vitals or set your thermostat. MIT researchers ...
50 million artificial neurons to facilitate machine-learning research

2020-10-02 352 neuromorphic

Fifty million artificial neurons—a number roughly equivalent to the brain of a small mammal—were delivered from Portland, Oregon-based Intel Corp. to Sandia National Laboratories last month, said Sandia project leader ...
Novel math could bring machine learning to the next level

2019-09-02 313 MachineLearning AI

A team of Italian mathematicians, including a neuroscientist from the Champalimaud Centre for the Unknown (CCU), in Lisbon, Portugal, has shown that artificial vision machines can learn to recognize complex images more quickly ...
Neuroscientists find a way to make object-recognition models perform better

2020-12-04 276

Computer vision models known as convolutional neural networks can be trained to recognize objects nearly as accurately as humans do. However, these models have one significant flaw: Very small changes to an image, which would ...
Developing brain atlas using deep learning algorithms

2018-07-23 232 BigData Datascience IoT

A team of researchers from the Brain Research Institute of the University of Zurich and the Swiss Federal Institute of Technology (ETH) have developed a fully automated brain registration method that could be used to segment ...
A deep learning technique to solve Rubik's cube and other problems step-by-step

2021-02-26 231

Colin G. Johnson, an associate professor at the University of Nottingham, recently developed a deep-learning technique that can learn a so-called "fitness function" from a set of sample solutions to a problem. This technique, ...
Using deep learning to control the unconsciousness level of patients in an anesthetic state

2020-09-25 225 HealthCare DeepLearning

In recent years, researchers have been developing machine learning algorithms for an increasingly wide range of purposes. This includes algorithms that can be applied in healthcare settings, for instance helping clinicians ...
AI outperforms humans in speech recognition

2020-10-20 217 AI

Following a conversation and transcribing it precisely is one of the biggest challenges in artificial intelligence (AI) research. For the first time now, researchers of Karlsruhe Institute of Technology (KIT) have succeeded ...
A deep learning-based method to detect cyberbullying on Twitter

2019-01-16 203 cyberbullying DeepLearning MachineLearning BigData

Researchers at King Saud University, in Saudi Arabia, have developed a new approach to detect cyberbullying on Twitter using deep learning called OCDD. In contrast with other deep-learning approaches, which extract features ...
Model helps robots think more like humans when searching for objects

2020-06-23 200

Robots can learn how to find things faster by learning how different objects around the house are related, according to work from the University of Michigan. A new model provides robots with a visual search strategy that ...
Scientists develop artificial intelligence system for high precision recognition of hand gestures

2020-08-13 198

Scientists from Nanyang Technological University, Singapore (NTU Singapore) have developed an Artificial Intelligence (AI) system that recognizes hand gestures by combining skin-like electronics with computer vision.
A technique to improve machine learning inspired by the behavior of human infants

2019-07-19 189 MachineLearning

From their first years of life, human beings have the innate ability to learn continuously and build mental models of the world, simply by observing and interacting with things or people in their surroundings. Cognitive psychology ...
Building machines that better understand human goals

2020-12-15 187

In a classic experiment on human social intelligence by psychologists Felix Warneken and Michael Tomasello, an 18-month old toddler watches a man carry a stack of books towards an unopened cabinet. When the man reaches the ...
Scientists use reinforcement learning to train quantum algorithm

2020-08-26 184

Recent advancements in quantum computing have driven the scientific community's quest to solve a certain class of complex problems for which quantum computers would be better suited than traditional supercomputers. To improve ...
Scientists build machine learning model for detecting early signs of depression in text

2020-07-24 181

A new machine learning model can detect early signs of depression in written text like Twitter posts, according to a study by University of Alberta computing scientists.