There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation a...
In this paper, we create a family of neural network (NN) operators employing a parametrized and deformed half-hyperbolic tangent function as an activation function and a density function produced by the same activation function. Moreover, we consider...
As a key step to endow the neural network with nonlinear factors, the activation function is crucial to the performance of the network. This paper proposes an Efficient Asymmetric Nonlinear Activation Function (EANAF) for deep neural networks. Compar...
The implementation of neural networks (NNs) on edge devices enables local processing of wireless data, but faces challenges such as high computational complexity and memory requirements when deep neural networks (DNNs) are used. Shallow neural networ...
The convolutional neural network (CNN) has been widely used in image recognition field due to its good performance. This paper proposes a facial expression recognition method based on the CNN model. Regarding the complexity of the hierarchic structur...
With the improvement of industrial requirements for the quality of cold rolled strips, flatness has become one of the most important indicators for measuring the quality of cold rolled strips. In this paper, the strip production data of a 1250 mm tan...
In the last years, materializations of neuromorphic circuits based on nanophotonic arrangements have been proposed, which contain complete optical circuits, laser, photodetectors, photonic crystals, optical fibers, flat waveguides and other passive o...
This study generalizes and further develops methods for efficiently implementing artificial neural networks (ANNs) in the onboard computers of mobile robotic systems with limited resources, including unmanned aerial vehicles (UAVs). The neural networ...
The activation function is a critical component in convolutional neural networks that perform nonlinear mappings between inputs and outputs. The rectified linear unit (ReLU) function is currently the baseline activation function in the deep learning...
Today, embedded systems (ES) tend towards miniaturization and the carrying out of complex tasks in applications such as the Internet of Things, medical systems, telecommunications, among others. Currently, ES structures based on artificial intelligen...
The study has modeled shoreline changes by using a multilayer perceptron (MLP) neural network with the data collected from five beaches in southern Taiwan. The data included aerial survey maps of the Forestry Bureau for years 1982, 2002, and 2006, wh...
In this work, we perform univariate approximation with rates, basic and fractional, of continuous functions that take values into an arbitrary Banach space with domain on a closed interval or all reals, by quasi-interpolation neural network operators...
Structure–function relationships in proteins have been one of the crucial scientific topics in recent research. Heme proteins have diverse and pivotal biological functions. Therefore, clarifying their structure–function correlation is sig...
Over the past few years, the Internet of Things (IoT) has been greatly developed with one instance being smart home devices gradually entering into people’s lives. To maximize the impact of such deployments, home-based activity recognition is r...
This study explores finite-time synchronization (FTS) in fractional-order quaternion-valued neural networks (FQVNNs) characterized by discontinuous activation functions and uncertainties in parameters. Initially, leveraging the properties of the Mitt...
With increasing real-time constraints being put on the use of Deep Neural Networks (DNNs) by real-time scenarios, there is the need to review information representation. A very challenging path is to employ an encoding that allows a fast processing a...
Modern microtechnology methods are widely used to create neural networks on a chip with a connection architecture demonstrating properties of modularity and hierarchy similar to brain networks. Such in vitro networks serve as a valuable model for stu...
Considering that chaotic systems are immersed in multiple areas of science and nature and that their dynamics are governed by a great sensitivity to the initial conditions and variations in their parameters, it is of great interest for the scientific...
Pneumonia remains a significant cause of morbidity and mortality among pediatric patients worldwide. Accurate and timely diagnosis is crucial for effective treatment and improved patient outcomes. Traditionally, pneumonia diagnosis has relied on a co...
Software estimation involves meeting a huge number of different requirements, such as resource allocation, cost estimation, effort estimation, time estimation, and the changing demands of software product customers. Numerous estimation models try to...
Landslide susceptibility mapping is well recognized as an essential element in supporting decision-making activities for preventing and mitigating landslide hazards as it provides information regarding locations where landslides are most likely to oc...
Flight behavior in pigeons is governed by intricate neural mechanisms that regulate movement patterns and flight dynamics. Among various kinematic parameters, flight acceleration provides critical information for the brain to modulate movement intens...
Inkjet-printed circuits on flexible substrates are rapidly emerging as a key technology in flexible electronics, driven by their minimal fabrication process, cost-effectiveness, and environmental sustainability. Recent advancements in inkjet-printed...
It is well known that feed-forward neural networks can be used for approximation to functions based on an appropriate activation function. In this paper, employing a new sigmoidal function with a parameter for an activation function, we consider a co...
This paper delves into the realm of human activity recognition (HAR) by leveraging the capabilities of Siamese neural networks (SNNs), focusing on the comparative effectiveness of contrastive and triplet learning approaches. Against the backdrop of H...
To solve the problems of high computational complexity and unstable image quality inherent in the compressive sensing (CS) method, we propose a complex-valued fully convolutional neural network (CVFCNN)-based method for near-field enhanced millimeter...
The nonlinearity of activation functions used in deep learning models is crucial for the success of predictive models. Several simple nonlinear functions, including Rectified Linear Unit (ReLU) and Leaky-ReLU (L-ReLU) are commonly used in neural netw...
We propose a neural-network-based watermarking method that introduces the quantized activation function that approximates the quantization of JPEG compression. Many neural-network-based watermarking methods have been proposed. Conventional methods ha...
Activation functions play a crucial role in ensuring training stability, convergence speed, and overall performance in both convolutional and attention-based networks. In this study, we introduce two novel activation functions, each incorporating a s...
I illustrate an approach that can be exploited for constructing neural networks that a priori obey physical laws. We start with a simple single-layer neural network (NN) but refrain from choosing the activation functions yet. Under certain conditions...
Due to the tremendous volume taken by the 3D point-cloud models, knowing how to achieve the balance between a high compression ratio, a low distortion rate, and computing cost in point-cloud compression is a significant issue in the field of virtual...
This work takes up the task of the determination of the rate of pointwise and uniform convergences to the unit operator of the “normalized cusp neural network operators”. The cusp is a compact support activation function, which is the com...
Suspension systems are critical parts of modern cars. In this study, a radial basis function neural networks-based adaptive PID optimal method is presented for vehicle suspension systems. To avoid the shortcoming that the parameters of PID control ar...
In this article, we study the multivariate quantitative smooth approximation under differentiation of functions. The approximators here are multivariate neural network operators activated by the symmetrized and perturbed hyperbolic tangent activation...
To address the challenges of high experimental costs, complexity, and time consumption associated with pre-mixed combustible gas deflagration experiments under semi-open space obstacle conditions, a rapid temporal prediction method for flame propagat...
The Squeeze-and-Excitation (SE) structure has been designed to enhance the neural network performance by allowing it to execute positive channel-wise feature recalibration and suppress less useful features. SE structures are generally adopted in a pl...
Essential neural-network operators are interpreted as positive linear operators, and the related general theory applies to them. These operators are induced by a symmetrized density function deriving from the parametrized and deformed A-generalized l...
The choice of the activation functions in neural networks (NN) are of paramount importance in the training process and the performance of NNs. Therefore, the machine learning community has directed its attention to the development of computationally...
The choice of activation functions and weight initialization strategies plays a critical role in the trainability and performance of deep neural networks. In deep architectures, improper weight initialization can lead to vanishing or exploding signal...
With high dimensionality and dependence in spatial data, traditional parametric methods suffer from the curse of dimensionality problem. The theoretical properties of deep neural network estimation methods for high-dimensional spatial models with dep...
Basic fuzzy multicomposite neural network operators are interpreted as fuzzy positive linear operators, and the related general fuzzy theory is applied. These fuzzy operators are defined by the composition of seven well-known activation functions. We...
In this article we present the
The physics-informed neural network (PINN) is an effective alternative method for solving differential equations that do not require grid partitioning, making it easy to implement. In this study, using automatic differentiation techniques, the PINN m...
In this article, we study the approximation properties of activated singular integral operators over the real line. We establish their convergence to the unit operator with rates. The kernels here derive from neural network activation functions and t...
In this work, three types of photopolymer printing plates for packaging printing were subjected to varied UV (ultraviolet radiation) post-treatments, and their surface free energy (SFE) components were calculated. SFE of the photopolymer printing pla...
Zeroing Neural Networks (ZNNs), an ODE-based neural dynamics framework, has become a pivotal approach for solving time-varying problems in dynamic systems. This paper systematically reviews recent advances in improving the convergence of ZNN models,...
CNNs and other deep learners are now state-of-the-art in medical imaging research. However, the small sample size of many medical data sets dampens performance and results in overfitting. In some medical areas, it is simply too labor-intensive and ex...
Accurate self-motion estimation is critical for various navigational tasks in mobile robotics. Optic flow provides a means to estimate self-motion using a camera sensor and is particularly valuable in GPS- and radio-denied environments. The present s...
Deep learning models are based on a combination of neural network architectures, optimization parameters and activation functions. All of them provide exponential combinations whose computational fitness is difficult to pinpoint. The intricate resemb...
Generative Adversarial Networks (GANs) have surfaced as a transformative approach in the domain of cryptography, introducing a novel paradigm where two neural networks, the generator (akin to Alice) and the discriminator (akin to Bob), are pitted aga...
of 37