AIMC Topic: Neurons

Clear Filters Showing 1361 to 1370 of 1455 articles

Hidden coexisting firings in fractional-order hyperchaotic memristor-coupled HR neural network with two heterogeneous neurons and its applications.

Chaos (Woodbury, N.Y.)
The firing patterns of each bursting neuron are different because of the heterogeneity, which may be derived from the different parameters or external drives of the same kind of neurons, or even neurons with different functions. In this paper, the di...

Phase-locking intermittency induced by dynamical heterogeneity in networks of thermosensitive neurons.

Chaos (Woodbury, N.Y.)
In this work, we study the phase synchronization of a neural network and explore how the heterogeneity in the neurons' dynamics can lead their phases to intermittently phase-lock and unlock. The neurons are connected through chemical excitatory conne...

Storage Capacity of Quaternion-Valued Hopfield Neural Networks With Dual Connections.

Neural computation
A complex-valued Hopfield neural network (CHNN) is a multistate Hopfield model. A quaternion-valued Hopfield neural network (QHNN) with a twin-multistate activation function was proposed to reduce the number of weight parameters of CHNN. Dual connect...

Randomized Self-Organizing Map.

Neural computation
We propose a variation of the self-organizing map algorithm by considering the random placement of neurons on a two-dimensional manifold, following a blue noise distribution from which various topologies can be derived. These topologies possess rando...

Organizing principles of the C. elegans contactome.

Cell systems
Two recent studies published in Nature generate and analyze, for the first time, the network of ∼100,000 membrane contacts between neurons in the C. elegans nerve ring. These novel data, extracted from legacy electron microscographs, represent a shif...

Skip-Connected Self-Recurrent Spiking Neural Networks With Joint Intrinsic Parameter and Synaptic Weight Training.

Neural computation
As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two pro...

Contrastive Similarity Matching for Supervised Learning.

Neural computation
We propose a novel biologically plausible solution to the credit assignment problem motivated by observations in the ventral visual pathway and trained deep neural networks. In both, representations of objects in the same category become progressivel...

The Remarkable Robustness of Surrogate Gradient Learning for Instilling Complex Function in Spiking Neural Networks.

Neural computation
Brains process information in spiking neural networks. Their intricate connections shape the diverse functions these networks perform. Yet how network connectivity relates to function is poorly understood, and the functional capabilities of models of...

Transition to synchronization in heterogeneous inhibitory neural networks with structured synapses.

Chaos (Woodbury, N.Y.)
Inhibitory neurons form an extensive network involved in the development of different rhythms in the cerebral cortex. A transition from an incoherent state, where all inhibitory neurons fire unrelated to each other, to a synchronized or locked state,...