Novel math could bring machine learning to the next level
Artificial vision networks can learn to recognize complex images faster by using topological data analysis.... Read More...
ANNs
Understanding the animal brain could help robots wash your dishes
A biological neural network which is sculpted by evolution provides a scaffolding to facilitate quick and easy learning.... Read More...
A computer that understands how you feel
EmoNet, a new convolutional neural network, can accurately decode images into eleven distinct emotional categories. Training the AI on over 25,000 images, researchers demonstrate image content is sufficient to predict the category and valence of human emotions. ... Read More...
Neuroscience and artificial intelligence can help improve each other
Researchers look at how neuroscience can help with artificial intelligence technology and vice versa.... Read More...
From one brain scan, more information for medical artificial intelligence
A convolutional neural network, designed by researchers at MIT, uses MRI datasets to find anatomical structures of the brain. The system could help in diagnosing and treating a range of brain conditions.... Read More...
AI software reveals the inner workings of short-term memory
A recurrent neural network algorithm demonstrates short-term synaptic plasticity can support short term maintenance of information, providing the memory delay period is sufficiently short.... Read More...
Outsmarting deep fakes: Researchers devise an AI-driven imaging system that protects authenticity
It might start to get easier to distinguish between real and fake images, thanks to a new deep learning system developed by NYU. The system is able to implant digital watermarks using an artificial neural network and spot manipulated photos and videos.... Read More...
Tempted to cheat on a written exam? Artificial intelligence is 90% certain to nab you
Using a Siamese neural network, a new deep learning system dubbed Ghostwriter is able to distinguish the writing styles between different texts. The algorithm compares a student's current written work against past examples of their prose, providing a percentage score for similar writing styles. The new system could be used to determine if a student has plagiarized their work, or if it is an original piece.... Read More...
Smarter training of neural networks
Researchers report artificial neural networks contain subnetworks that are considerably smaller, yet capable of being trained to make equally accurate predictions. Many subnetworks can learn to make accurate predictions much faster than the original networks.... Read More...
Artificial neural networks can be used to drive brain activity
Current deep learning models are able to create images strongly enough to activate specific neurons in the visual cortex. However, researchers say more accurate artificial neural network models should be developed to help produce more accurate control.... Read More...
Artificial intelligence singles out neurons faster than a human can
Convolutional neural network model significantly outperforms previous methods and is as accurate as humans in segmenting active and overlapping neurons.... Read More...
Robots to autocomplete soldier tasks
Study uncovers how the brain coordinates between different regions while executing cognitive tasks. The findings may help advance artificial intelligence algorithms.... Read More...