In this paper we study the well-posedness as well as the stabilization properties of the swelling porous elastic media with structural damping acting on both equations of the system. By using semigroup theory, we prov...
详细信息
Population-based computational intelligence algorithms are natural candidates for parallelization and have been utilized to solve a variety of difficult and complex real-world problems. The gray wolf optimizer (GWO) i...
详细信息
This paper performs a classification task on data obtained from the Autism Brain Imaging Data Exchange (ABIDE) repository. In real-world case analysis, the number of autism spectrum disorder (ASD) patients is much sma...
详细信息
In this paper, we consider the Shear beam model (no rotary inertia) and we stablished a decay result of the total energy of solutions by taking a feedback law acting on angle rotation. Unlike the dissipative Shear bea...
详细信息
Behavioral changes in animals and humans, as a consequence of an error or a verbal instruction, can be extremely rapid. Improvement in behavioral performances are usually associated learning theories to synaptic plast...
详细信息
Behavioral changes in animals and humans, as a consequence of an error or a verbal instruction, can be extremely rapid. Improvement in behavioral performances are usually associated learning theories to synaptic plasticity. However, such rapid changes are not coherent with the timescales of biological synaptic plasticity, suggesting that the mechanism responsible for that could be a dynamical reconfiguration of the network involved, without changing its weights. In the last few years, similar capabilities have been observed in transformers, foundational architecture in the field of machine learning that are widely used in applications such as natural language and image processing. Transformers are capable of in-context learning, the ability to adapt and acquire new information dynamically within the context of the task or environment they are currently engaged in, without the need for significant changes to their underlying parameters. Building upon the notion of something unique within transformers enabling the emergence of this property, we claim that it could be supported by gain-modulation, feature extensively observed in biological networks, such as in pyramidal neurons thanks to input segregation and dendritic amplification. We propose a constructive approach to induce in-context learning in an architecture composed of recurrent networks with gain modulation, demonstrating abilities inaccessible to standard networks. In particular, we show that, such architecture can dynamically implement standard gradient-based by encoding weight changes in the activity of another network. We argue that, while these algorithms are traditionally associated with synaptic plasticity, their reliance on non-local terms suggests that, in the brain, they can be more naturally realized at the level of neural circuits. We demonstrate that we can extend our approach to non-linear and temporal tasks and to reinforcement learning. We further validate our approach in a realistic robotic s
A finite-area holomorphic quadratic differentials on an arbitrary Riemann surface X = H/Γ is uniquely determined by its horizontal measured foliation. By extending our prior result for Γ of the first kind to arbitra...
详细信息
We introduce a notion of a bounded ideal triangulation of an infinite Riemann surface and parametrize Teichmüller spaces of infinite surfaces which allow bounded triangulations. We prove that our parametrization ...
详细信息
This paper performs a classification task on data obtained from the Autism Brain Imaging Data Exchange (ABIDE) repository. In real-world case analysis, the number of autism spectrum disorder (ASD) patients is much sma...
详细信息
ISBN:
(数字)9798350396133
ISBN:
(纸本)9798350396140
This paper performs a classification task on data obtained from the Autism Brain Imaging Data Exchange (ABIDE) repository. In real-world case analysis, the number of autism spectrum disorder (ASD) patients is much smaller than typically developed people. To address this issue, this paper proposes the utilization of pairwise robust support vector machine (PRSVM) algorithms to classify autism spectrum disorder (ASD) patients. In this project's experiments, the correlation matrix derived from functional magnetic resonance imaging (fMRI) data was employed as a classification feature. A comprehensive evaluation was conducted to compare the classification performance of PRSVM with various machine learning methods. The comparative analysis encompassed various aspects, including different data dimensions, imbalanced ratios, and sample sizes, providing valuable insights into the relative performance of the algorithms under different experimental conditions. The experimental results demonstrate that PRSVM can detect autistic patients more accurately when the data is imbalanced. Moreover, the results indicate that PRSVM outperforms or achieves comparable performance to other conventional classification methods in a variety of situations. Furthermore, our approach can be further improved by augmenting the training set with either exclusively normal person samples or by incorporating patient samples and normal people samples in a proportionate manner. This augmentation strategy holds promising application value, as it contributes to improving the performance and robustness of our method.
For a fixed cusp neighborhood (determined by depth D) of the modular surface, we investigate the class of reciprocal geodesics that enter this neighborhood (called a cusp excursion) a fixed number of times. Since reci...
详细信息
Population-based computational intelligence algorithms are natural candidates for parallelization and have been utilized to solve a variety of difficult and complex real-world problems. The gray wolf optimizer (GWO) i...
Population-based computational intelligence algorithms are natural candidates for parallelization and have been utilized to solve a variety of difficult and complex real-world problems. The gray wolf optimizer (GWO) is one of these algorithms. It is a metaheuristic that simulates the leadership hierarchy and hunting mechanism of gray wolves in the wild and has been used successfully to solve several hard optimization problems. However, the study of its applicability to the solution of nonlinear equation systems, which is arguably the most difficult class of numerical problems, is still quite incipient and needs to be better accessed and verified, particularly in the case of large-scale systems of nonlinear equations, which have not been considered until now and whose resolution difficulty increases with the number of equations they contain. This paper presents a new and efficient GPU-based massively parallel implementation of the gray wolf optimizer algorithm for solving large-scale optimization problems. The proposed parallelization of the GWO algorithm is illustrated by its application to solving large systems of nonlinear equations, a class of problems that appear and have great importance in different fields of pure and applied sciences and engineering. The GPU-accelerated version of GWO was implemented in Julia and tested on a GeForce RTX 3090 GPU with 24 GB GDDR6X VRAM and 10 496 CUDA cores using a set of hard, scalable systems of nonlinear equations with dimensions ranging from 500 to 2000. The obtained results, with average speedups between 69.91× and 241.54× , show the efficiency of the proposed GPU-based acceleration of the GWO algorithm.
暂无评论