Nature communications
Jun 9, 2022
We propose an approach to learn effective evolution equations for large systems of interacting agents. This is demonstrated on two examples, a well-studied system of coupled normal form oscillators and a biologically motivated example of coupled Hodg...
Neural networks : the official journal of the International Neural Network Society
Jun 7, 2022
The vanishing gradient problem (i.e., gradients prematurely becoming extremely small during training, thereby effectively preventing a network from learning) is a long-standing obstacle to the training of deep neural networks using sigmoid activation...
Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
Jun 6, 2022
This paper describes a fully experimental hybrid system in which a [Formula: see text] memristive crossbar spiking neural network (SNN) was assembled using custom high-resistance state memristors with analogue CMOS neurons fabricated in 180 nm CMOS t...
IEEE transactions on pattern analysis and machine intelligence
Jun 3, 2022
Neural architecture search (NAS) has attracted a lot of attention and has been illustrated to bring tangible benefits in a large number of applications in the past few years. Architecture topology and architecture size have been regarded as two of th...
Nature communications
Jun 3, 2022
Neuromorphic computing, a computing paradigm inspired by the human brain, enables energy-efficient and fast artificial neural networks. To process information, neuromorphic computing directly mimics the operation of biological neurons in a human brai...
IEEE/ACM transactions on computational biology and bioinformatics
Jun 3, 2022
Analog DNA strand displacement circuits can be used to build artificial neural network due to the continuity of dynamic behavior. In this study, DNA implementations of novel catalysis, novel degradation and adjustment reaction modules are designed an...
Computational intelligence and neuroscience
Jun 2, 2022
This paper presents a methodology for synchronizing noisy and nonnoisy multiple coupled neurobiological FitzHugh-Nagumo (FHN) drive and slave neural networks with and without delayed coupling, under external electrical stimulation (EES), external dis...
Science robotics
Jun 1, 2022
An electronic skin (e-skin) for the next generation of robots is expected to have biological skin-like multimodal sensing, signal encoding, and preprocessing. To this end, it is imperative to have high-quality, uniformly responding electronic devices...
eLife
May 30, 2022
Neural systems are remarkably robust against various perturbations, a phenomenon that still requires a clear explanation. Here, we graphically illustrate how neural networks can become robust. We study spiking networks that generate low-dimensional r...
Journal of neural engineering
May 30, 2022
. In the theoretical framework of predictive coding and active inference, the brain can be viewed as instantiating a rich generative model of the world that predicts incoming sensory data while continuously updating its parameters via minimization of...