A biologically plausible network model for pattern storage and recall inspired by Dentate Gyrus
- PDF / 1,030,705 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 34 Downloads / 158 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
A biologically plausible network model for pattern storage and recall inspired by Dentate Gyrus V. Vidya Janarthanam1
•
S. Vishwanath1 • A. P. Shanthi1
Received: 12 October 2018 / Accepted: 6 December 2019 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract In the race to achieve better performance, artificial intelligence has become more about the end rather than the means, which is general intelligence. This work aims to bridge the gap between the two by finding a complementary midline. The objective of this work is to project the role of Dentate Gyrus in enhancing the performance of an autoassociative network, paving the way to develop a biologically plausible neural network which, in the future, would help in simulating the network present in our brain. The proposed network imbibes biological similarities with respect to connectivity, weight updation, and activation function. Dentate Gyrus uses pre-integration lateral inhibition form of learning, and the autoassociative network is implemented using Hopfield network. The performance of the autoassociative network in the presence and absence of Dentate Gyrus is observed across multiple parameters. The results show an increase of 38% in storage capacity and a decrease of 15% in the error tolerance capability of the network in the presence of Dentate Gyrus. Keywords CA3 Memory Hippocampus Hopfield network DG
1 Introduction Artificial general intelligence has remained a holy grail for AI researchers, while working of the neural network in our brain has remained a mystery for neuroscience researchers worldwide. With breakthroughs in the field of neuroscience, neuroimaging, and cognitive science, a better picture has emerged. Harnessing these findings and the increase in computation power, this work proposes the first step toward building a network functionally similar to the brain in silico. Any intelligent system, artificial or biological, requires a knowledge base, and the purpose of building a knowledge base is fulfilled only when it stores and retrieves data effectively and efficiently. If we want to achieve humanlevel intelligence in the future, we need to structure and process knowledge like humans do. So, the question is where do we start? The answer lies in the region known as hippocampus in our brain, which plays a major role in & V. Vidya Janarthanam [email protected]; [email protected] 1
Department of Computer Science and Engineering, College of Engineering, Guindy, Anna University, Chennai, India
memory storage and retrieval. It can be considered as a code book for the knowledge stored in our brain, and it is also responsible for creating the code book. Hippocampus is a part of the archicortex, the oldest region of the brain. Being one of the earliest regions to develop, it can be said that hippocampus is the starting point of the evolutionary road leading to memory and intelligence as we know it today. The role of hippocampus in memory has been an
Data Loading...
