Integration of Brain Connectomics and ANN will strengthen brain’s ability for cognitive performances

Deep learning is a part of machine learning that is based on artificial neural networks (ANNs). Deep learning executes engineering features on its own. Deep learning algorithms can create transferable solutions through neural networks, or layers of neurons, units. 

 

Deep learning is used in multiple domains, the healthcare industry and automated driving cars leverage the advantages of deep learning. In the automated cars, deep learning is helpful in the detection of traffic lights, pedestrians or other hurdles that might come in the way of autonomous vehicles. 

 

(Must Check: When Artificial Intelligence (AI) And Neuroscience Meet)

 

For further progression in the field of Deep Learning, researchers from Montreal Neurological Hospital and Quebec Artificial Intelligence Institute trained an artificial neural network for performance in cognitive memory task. 

 

Cognitive Memory Tasks are performed to assess the brain's retaining capacity. These assessments are usually undertaken to calculate people’s EQ and IQ levels. Different types of assessment tools are employed for evaluating the brain’s intelligent quotient. 

 

Connectomics, is one such field that focuses on drawing a link between brain structure and its functional non/functional connection with the cells. Researchers attached brain connectomics into the artificial neural network. 

 

In simple words brain connectomics is a wiring of neural connections inside the human brain. Connectomics are integral for the brain's proper functioning. They help in mapping and generating neurons in large volumes. 

 

Results of the Research

 

Researchers connected brain connectomics into the creation of ANN architectures. By the integration of the duo researchers learnt about the wiring of the brain. Research also revealed insights about the brain's specific functions. 

 

Researchers discovered that neuromorphic neural networks are efficient in the performance of cognitive tasks. Neuromorphic neural networks followed a similar architecture to perform tasks in a variety of contexts. 

 

According to Tech Explore Bratislav Misic, a researcher at The Neuro and the paper's senior author said, “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 understand how brain structure supports brain function. In turn, using empirical data to make neural networks will reveal design principles for building better AI”.