Search
Search Results
-
Universal structural patterns in sparse recurrent neural networks
Sparse neural networks can achieve performance comparable to fully connected networks but need less energy and memory, showing great promise for...
-
Graph neural networks
Graphs are flexible mathematical objects that can represent many entities and knowledge from different domains, including in the life sciences. Graph...
-
Neural Networks for Processing Nuclear Emulsions
AbstractOwing to the development of optical precision and computer technology, the number of experiments based on visual methods for processing data...
-
Quantifying unknown entanglement by neural networks
Quantum entanglement plays a crucial role in quantum information processing tasks and quantum mechanics; hence, quantifying unknown entanglement is a...
-
Solitonic Neural Networks An Innovative Photonic Neural Network Based on Solitonic Interconnections
This book delves into optics and photonic materials, describing the development of an intelligent all-optical system capable of replicating the...
-
Enhancing the expressivity of quantum neural networks with residual connections
In noisy intermediate-scale quantum era, the research on the combination of artificial intelligence and quantum computing has been greatly developed....
-
ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
The barren plateau problem in quantum neural networks (QNNs) is a significant challenge that hinders the practical success of QNNs. In this paper, we...
-
Stability of Cohen–Grossberg Neural Networks with Time-Dependent Delays
AbstractThe work is devoted to the analysis of Lyapunov stability of Cohen–Grossberg neural networks with time-dependent delays. For this, the...
-
Using Hidden Feature Space of Diffusion Neural Networks for Image Blending Problem
AbstractIn this paper, a new augmentation algorithm based on the idea of blending two images is proposed. The method is developed using...
-
Strong generalization in quantum neural networks
Generalization is an important feature of neural networks (Nns) as it indicates their ability to predict new and unknown data. However, classical Nns...
-
Fractional discrete neural networks with variable order: solvability, finite time stability and synchronization
Research in the field of dynamic behaviors in neural networks with variable-order differences is currently a thriving area, marked by various...
-
Entanglement Detection with Complex-Valued Neural Networks
A key problem of quantum information processing is to determine whether a given quantum state is entangled. In this work, we utilize complex-valued...
-
Image optical processing based on convolutional neural networks in sports video recognition simulation
The demand of sports video recognition simulation is increasing, but the traditional methods have some limitations in dealing with optical problems....
-
Artificial Neural Networks
In this chapter, we provide a short overview of the basics of neural networks. We still do not have a deep understanding of the training process of... -
Deep learning with coherent VCSEL neural networks
Deep neural networks (DNNs) are resha** the field of information processing. With the exponential growth of these DNNs challenging existing...
-
Analysis of oscillating processes in spiking neural networks
In the classical neural networks, information is presented as a set of the stable equilibrium states. This review considers a series of papers...
-
Control of mediated stochastic resonance in multilayer neural networks
This study focuses on exploring noise-induced dynamics in multilayer neural networks consisting of FitzHugh–Nagumo (FHN) neurons. Initially, a...
-
Machine learning with neural networks for parameter optimization in twin-field quantum key distribution
Twin-field quantum key distribution (TF-QKD) has the advantage of beating the rate-loss limit (PLOB bound) for a repeaterless quantum key...
-
Modulated nerve impulse solution of memristive photosensitive neural networks
In this paper, a clear analytical approach is performed to show the emergence and propagation of traveling modulated nerve impulse signal in a...
-
Bicomplex Neural Networks with Hypergeometric Activation Functions
Bicomplex convolutional neural networks (BCCNN) are a natural extension of the quaternion convolutional neural networks for the bicomplex case. As it...