A new machine-learning algorithm is able to teach itself to smell within a few minutes of training. As it learns, the system builds an artificial network that mimics the brain's olfactory system.
Researchers discuss different current neural network models and consider the steps that need to be taken to make them more realistic, and thus more useful, as possible.
Artificial IntelligenceAutismDeep LearningFeaturedMachine LearningNeuroscienceOpen Neuroscience Articles··3 min read
Artificial neural networks help researchers uncover new clues as to why people on the autism spectrum have trouble interpreting facial expressions.
Researchers propose a novel computational framework that uses artificial intelligence technology to disentangle the relationship between perception and memory in the human brain.
A new deep learning algorithm is superior to human experts in distinguishing between retinal ganglion cells in healthy patients and in those with glaucoma. The AI system could potentially help improve the diagnosis of both eye and brain diseases.
When convolutional neural networks are trained under experimental conditions, they are deceived by the brightness and color of a visual image in similar ways to the human visual system.