AI Networks Modelled on Human Brain Connectivity Can Execute Cognitive Tasks


Cognitive tasks are often performed by artificial neural networks modeled after real brains.A new study reveals that AI networks supported human brain connectivity can perform intellectual tasks efficiently.Researchers reconstructed a brain connectivity pattern using MRI data from an outsized Open Science repository and applied it to a man-made neural network (ANN). An ANN may be a computer system that,

just like the biological brain, has multiple input and output units.A team of researchers from The Neuro (Montreal Neurological Institute-Hospital) and therefore the Quebec AI Institute trained the ANN to finish a cognitive memory task and observed how it performed.Previous research on brain connectivity, also referred to as connectomics,

targeting describing brain organization instead of how it performs computations and functions.Traditional ANNs have arbitrary structures that don’t reflect the organization of real brain networks. Researchers hoped that by incorporating brain connectomics into the planning of ANN architectures,

they might be ready to find out how the wiring of the brain supports specific cognitive skills also as derive novel design principles for artificial networks.They discovered that neuromorphic neural networks, or ANNs with human brain connectivity, performed cognitive memory tasks more flexibly and efficiently than other benchmark architectures.The neuromorphic neural networks were ready to support a good range of learning capacities across multiple contexts by using an equivalent underlying architecture.Bratislav Misic,

a researcher at The Neuro and therefore the paper’s senior author, says, “The project unifies two vibrant and fast-paced scientific disciplines.”“Neuroscience and AI share common roots but have recently diverged. Using artificial networks will help us to know how brain structure supports brain function. In turn, using empirical data to form neural networks will reveal design principles for building better AI. So, the 2 will help inform one another and enrich our understanding of the brain.”


Please enter your comment!
Please enter your name here