Cellular neural network
View article: Cellular deconvolution of the brain with topological magnetic resonance image analysis
Cellular deconvolution of the brain with topological magnetic resonance image analysis Open
Magnetic resonance imaging (MRI) is foundational tool in neuroscience, enabling characterization of neuroanatomical markers of disease, behavior, and cognition. However, the precise cellular processes driving the structural and functional …
View article: Memristive Hopfield Neural Network with Hidden Multiple Attractors and Its Application in Color Image Encryption
Memristive Hopfield Neural Network with Hidden Multiple Attractors and Its Application in Color Image Encryption Open
Memristor is widely used to construct various memristive neural networks with complex dynamical behaviors. However, hidden multiple attractors have never been realized in memristive neural networks. This paper proposes a novel chaotic syst…
View article: Conditional Morphogenesis: Emergent Generation of Structural Digits via Neural Cellular Automata
Conditional Morphogenesis: Emergent Generation of Structural Digits via Neural Cellular Automata Open
Biological systems exhibit remarkable morphogenetic plasticity, where a single genome can encode various specialized cellular structures triggered by local chemical signals. In the domain of Deep Learning, Differentiable Neural Cellular Au…
View article: Conditional Morphogenesis: Emergent Generation of Structural Digits via Neural Cellular Automata
Conditional Morphogenesis: Emergent Generation of Structural Digits via Neural Cellular Automata Open
Biological systems exhibit remarkable morphogenetic plasticity, where a single genome can encode various specialized cellular structures triggered by local chemical signals. In the domain of Deep Learning, Differentiable Neural Cellular Au…
View article: An Asynchronous Mixed-Signal Resonate-and-Fire Neuron
An Asynchronous Mixed-Signal Resonate-and-Fire Neuron Open
Analog computing at the edge is an emerging strategy to limit data storage and transmission requirements, as well as energy consumption, and its practical implementation is in its initial stages of development. Translating properties of bi…
View article: An Asynchronous Mixed-Signal Resonate-and-Fire Neuron
An Asynchronous Mixed-Signal Resonate-and-Fire Neuron Open
Analog computing at the edge is an emerging strategy to limit data storage and transmission requirements, as well as energy consumption, and its practical implementation is in its initial stages of development. Translating properties of bi…
View article: Hepta-Senary Homeostatic Cell (H⁷-Cell): The First Proto-Organism Model for Emergent Digital Life in Senary Computation
Hepta-Senary Homeostatic Cell (H⁷-Cell): The First Proto-Organism Model for Emergent Digital Life in Senary Computation Open
This publication introduces the Hepta-Senary Homeostatic Cell (H⁷-Cell), the world’s first digital proto-organism model designed natively for senary computational geometry.The H⁷-Cell represents a new class of artificial life: a homeostati…
View article: Hepta-Senary Homeostatic Cell (H⁷-Cell): The First Proto-Organism Model for Emergent Digital Life in Senary Computation
Hepta-Senary Homeostatic Cell (H⁷-Cell): The First Proto-Organism Model for Emergent Digital Life in Senary Computation Open
This publication introduces the Hepta-Senary Homeostatic Cell (H⁷-Cell), the world’s first digital proto-organism model designed natively for senary computational geometry.The H⁷-Cell represents a new class of artificial life: a homeostati…
View article: An all-optical convolutional neural network for image identification
An all-optical convolutional neural network for image identification Open
In modern artificial intelligence, convolutional neural networks (CNNs) have become a cornerstone for visual and perceptual tasks. However, their implementation on conventional electronic hardware faces fundamental bottlenecks in speed and…
View article: An all-optical convolutional neural network for image identification
An all-optical convolutional neural network for image identification Open
In modern artificial intelligence, convolutional neural networks (CNNs) have become a cornerstone for visual and perceptual tasks. However, their implementation on conventional electronic hardware faces fundamental bottlenecks in speed and…
View article: Image Processing Based on Convolution Neural Network
Image Processing Based on Convolution Neural Network Open
In today’s digital age, images serve as vital information carriers that are widely deployed across a diverse range of fields, including healthcare, security, transportation, and entertainment [...]
View article: QuFeX: Quantum Feature Extraction module for hybrid quantum-classical deep neural networks
QuFeX: Quantum Feature Extraction module for hybrid quantum-classical deep neural networks Open
We introduce Quantum Feature Extraction (QuFeX), a novel quantum machine learning module. The proposed module enables feature extraction in a reduced-dimensional space, significantly decreasing the number of parallel evaluations required i…
View article: Advanced physics-informed neural networks for nonlinear partial differential equations: machine learning, gradient-enhanced and extended approach
Advanced physics-informed neural networks for nonlinear partial differential equations: machine learning, gradient-enhanced and extended approach Open
View article: Homeostatic neural networks: math and report
Homeostatic neural networks: math and report Open
STONIAN CLONAL ROOT SYSTEM ALGORITHMIC PARADIGM Architect: Travis Raymond-Charlie Stone Framework: Stonian Persistent Neural Fabric (SPNF) 1. System Overview This paradigm treats a computational system the way a clonal root organism functi…
View article: Neural Calculus: Learning Continuous Transformations and Accumulations
Neural Calculus: Learning Continuous Transformations and Accumulations Open
This paper introduces Neural Calculus, a novel framework that integrates the fundamental principles of calculus into neural network architectures. The primary objective is to develop models capable of learning continuous transformations an…
View article: Neural Calculus: Learning Continuous Transformations and Accumulations
Neural Calculus: Learning Continuous Transformations and Accumulations Open
This paper introduces Neural Calculus, a novel framework that integrates the fundamental principles of calculus into neural network architectures. The primary objective is to develop models capable of learning continuous transformations an…
View article: Homeostatic neural networks: math and report
Homeostatic neural networks: math and report Open
STONIAN CLONAL ROOT SYSTEM ALGORITHMIC PARADIGM Architect: Travis Raymond-Charlie Stone Framework: Stonian Persistent Neural Fabric (SPNF) 1. System Overview This paradigm treats a computational system the way a clonal root organism functi…
View article: A survey on convolutional neural network hardware acceleration through approximate computing multiple and accumulates unit
A survey on convolutional neural network hardware acceleration through approximate computing multiple and accumulates unit Open
Convolutional neural networks (CNNs) are applied to a different range of real-world complex tasks to provide effective solutions with high accuracy. Based on the application's complexity, CNN demands a lot of processing units and memory sp…
View article: Neural Calculus: Learning Continuous Transformations and Accumulations
Neural Calculus: Learning Continuous Transformations and Accumulations Open
This paper introduces Neural Calculus, a novel framework that integrates the fundamental principles of calculus into neural network architectures. The primary objective is to develop models capable of learning continuous transformations an…
View article: A real-valued DCT-based spectral CNN architecture for efficient edge deep learning
A real-valued DCT-based spectral CNN architecture for efficient edge deep learning Open
View article: Deep oscillatory neural network
Deep oscillatory neural network Open
We propose the Deep Oscillatory Neural Network (DONN), a brain-inspired network architecture that incorporates oscillatory dynamics into learning. Unlike conventional neural networks with static internal states, DONN neurons exhibit brain-…
View article: A multi-synaptic memristor-based neural network and its encryption application
A multi-synaptic memristor-based neural network and its encryption application Open
View article: Convolutional Neural Networks with Quantum Inspiration: An Approach to Improved EEG Signal Processing
Convolutional Neural Networks with Quantum Inspiration: An Approach to Improved EEG Signal Processing Open
The research now proceeds to handle the problems of traditional methods with noise and integrity issues of EEG signals by implementing a quantum-inspired CNN for developing signal processing. The model provides enhanced performance in feat…
View article: Global synchronization in Matrix-Weighted networks
Global synchronization in Matrix-Weighted networks Open
Synchronization phenomena in complex systems are fundamental to understanding collective behavior across disciplines. While classical approaches model such systems by using scalar-weighted networks and simple diffusive couplings, many real…
View article: Do All the Theoretical Results Obtained in the Case of Hopfield Neural Networks Have a Counterpart at the Level of the Human Neural System?
Do All the Theoretical Results Obtained in the Case of Hopfield Neural Networks Have a Counterpart at the Level of the Human Neural System? Open
Continuous and discrete Hopfield type neural networks claim to be mathematical descriptions of electrical phenomena appearing in nervous system. We present a set of theoretical results having natural counterpart and another set of theoreti…
View article: Multi-texture synthesis through signal responsive neural cellular automata
Multi-texture synthesis through signal responsive neural cellular automata Open
Neural Cellular Automata have proven to be effective in various fields, with numerous biologically inspired applications. Particularly, neural cellular automata have been proven to be successful models for procedural generation of textures…
View article: Semi-Intermittent Control Based Fixed/Predefined-Time Synchronization of Spatiotemporal Memristive Neural Networks
Semi-Intermittent Control Based Fixed/Predefined-Time Synchronization of Spatiotemporal Memristive Neural Networks Open
This article addresses the fixed-time (FXT) and predefined-time (PDT) synchronization issues of spatiotemporal memristive neural networks (MNNs). First, an aperiodic semi-intermittent control (ASIC) scheme is introduced to reduce the contr…
View article: Intelligent Hybrid Image Encryption Using Adaptive Neural Permutation and Chaotic Key Dynamics
Intelligent Hybrid Image Encryption Using Adaptive Neural Permutation and Chaotic Key Dynamics Open
In the era of digital imagery, in critical applications like healthcare, defense and private communication, there is a true need for strong, computationally secure encryption techniques. Traditional cryptographic algorithms, though optimal…
View article: FG-PINNs: frequency-guided physics-informed neural networks for solving PDEs with high frequency components
FG-PINNs: frequency-guided physics-informed neural networks for solving PDEs with high frequency components Open
In this work, we propose the frequency-guided physics-informed neural networks (FG-PINNs), specifically designed for solving partial differential equations (PDEs) with high-frequency components. The core of the proposed algorithm lies in u…
View article: Correction to: Automatic Differentiation Is Essential in Training Neural Networks for Solving Differential Equations
Correction to: Automatic Differentiation Is Essential in Training Neural Networks for Solving Differential Equations Open