deep neural networks

The code mimics the mechanisms by which the immune system learns to identify antigens, instead learning to characterize the dubious inputs to the machine learning algorithm. Image credit: Ren Wang
A way to make deep neural networks immune to hacking?
The code mimics the mechanisms by which the immune system learns to identify antigens, instead
Quizzing artificial intelligence to see what rules it learned on its own and if they are the right ones
Cold Spring Harbor Laboratory Assistant Professor Peter Koo in his lab with graduate student Shushan
CPU algorithm trains deep neural nets up to 15 times faster than top GPU trainers
Anshumali Shrivastava, Shabnam Daghaghi, Nicholas Meisburger CPU algorithm trains deep neural nets up to 15
New artificial intelligence software moves robots assisting humans in warehouse environments MUCH closer
UC Berkeley engineers have created new software that combines neural networks with motion planning software
Understanding when not to trust AI-assisted decision-making
via MIT Understanding when not to trust AI-assisted decision-making A neural network learns when it
Solved: A major long-standing obstacle to increasing AI capabilities has been “catastrophic forgetting”
via Baylor College of Medicine Solved: A major long-standing obstacle to increasing AI capabilities has
Training deep neural networks using 10 times less energy

Green AI can open the door enabling researchers with a laptop or limited computational resources to explore AI innovations

Fighting deep fakes with a deep neural network

Artificial intelligence to accurately detect altered photos is getting smarter Seeing was believing until technology

Drones acquire the ability for a much smoother landing thanks to new AI called Neural Lander

New system employs a deep neural network to overcome the challenge of ground-effect turbulence Landing

Boosting memory of AI systems to better learn new tasks while forgetting less of what was learned in previous tasks

A project of the U.S. Army has developed a new framework for deep neural networks

A new framework for deep neural networks improves continual learning for artificial intelligence

Researchers have developed a new framework for deep neural networks that allows artificial intelligence (AI)

Deep learning speeds up the design and creation of metamaterials

Tel Aviv University researchers devise new approach to streamlining design of nanoscale building blocks with

Deep neural networks could detect magnetic field anomalies for faster warnings before earthquakes and tsunamis

Researchers from Tokyo Metropolitan University have applied machine-learning techniques to achieve fast, accurate estimates of