Simulation of neural function in an artificial Hebbian network
This addresses inefficiencies in neural network training for researchers and practitioners, but appears incremental as it builds on known biological principles.
The authors tackled the problem of artificial neural networks diverging from biological principles and requiring large training data and computational resources by proposing a neurological network simulation that adheres more closely to biology, overcoming some shortcomings of conventional networks.
Artificial neural networks have diverged far from their early inspiration in neurology. In spite of their technological and commercial success, they have several shortcomings, most notably the need for a large number of training examples and the resulting computation resources required for iterative learning. Here we describe an approach to neurological network simulation, both architectural and algorithmic, that adheres more closely to established biological principles and overcomes some of the shortcomings of conventional networks.