神经与进化计算
The challenging deployment of compute- and memory-intensive methods from Deep Neural Network (DNN)-based Continual Learning (CL) underscores the critical need for a paradigm shift towards more efficient approaches. Neuromorphic Continual…
This article proposes a method to formalise models of cognitive processes grounded in experience, considering experience from the perspective of a living system and not from that of an observer of the living system. The perspective of a…
This paper investigates the development of high-performance racing controllers for a newly implemented racing mode within the Xpilot-AI platform, utilizing the Neuro Evolution of Augmenting Topologies (NEAT) algorithm. By leveraging NEAT's…
Bio-inspired neural networks are attractive for their adversarial robustness, energy frugality, and closer alignment with cortical physiology, yet they often lag behind back-propagation (BP) based models in accuracy and ability to scale. We…
Generative adversarial networks (GANs) are powerful generative models but remain challenging to train due to pathologies suchas mode collapse and instability. Recent research has explored co-evolutionary approaches, in which populations of…
Image classification currently faces significant security challenges due to adversarial attacks, which consist of intentional alterations designed to deceive classification models based on artificial intelligence. This article explores an…
Despite tremendous progress in neuroscience, we do not have a compelling narrative for the precise way whereby the spiking of neurons in our brain results in high-level cognitive phenomena such as planning and language. We introduce a…
Identifying similar documents within extensive volumes of data poses a significant challenge. To tackle this issue, researchers have developed a variety of effective distributed computing techniques. With the advancement of computing power…
In this paper, we introduce Hebbian learning as a novel method for swarm robotics, enabling the automatic emergence of heterogeneity. Hebbian learning presents a biologically inspired form of neural adaptation that solely relies on local…
This article addresses theory in evolutionary many-objective optimization and focuses on the role of crossover operators. The advantages of using crossover are hardly understood and rigorous runtime analyses with crossover are lagging far…
The complete connectome of the Drosophila larva brain offers a unique opportunity to investigate whether biologically evolved circuits can support artificial intelligence. We convert this wiring diagram into a Biological Processing Unit…
In this study we introduce a symbolic dataset composed of non-metric Iranian classical music, and algorithms for structural parsing of this music, and generation of variations. The corpus comprises MIDI files and data sheets of Dastgah…
With increasing wastewater rates, achieving energy-neutral purification is challenging. We introduce a coral-reef-inspired Swarm Interaction Network for carbon-neutral wastewater treatment, combining morphogenetic abstraction with…
Activation functions are key to effective backpropagation and expressiveness in deep neural networks. This work introduces Tangma, a new activation function that combines the smooth shape of the hyperbolic tangent with two learnable…
Achieving carbon neutrality, a key focus of UN SDG #13, drives the exploration of wave energy, a renewable resource with the potential to generate 30,000 TWh of clean electricity annually, surpassing global demand. However, wave energy…
Fraud detection is one of the most important challenges that financial systems must address. Detecting fraudulent transactions is critical for payment gateway companies like Flow Payment, which process millions of transactions monthly and…
Spiking Neural Networks (SNNs) have the potential to drastically reduce the energy requirements of AI systems. However, mainstream accelerators like GPUs and TPUs are designed for the high arithmetic intensity of standard ANNs so are not…
Continuous graph neural networks (CGNNs) have garnered significant attention due to their ability to generalize existing discrete graph neural networks (GNNs) by introducing continuous dynamics. They typically draw inspiration from…
The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks (GNNs) is gradually attracting attention due to the low power consumption and high efficiency in processing the non-Euclidean data represented by graphs. However,…
Parameter control and dynamic algorithm configuration study how to dynamically choose suitable configurations of a parametrized algorithm during the optimization process. Despite being an intensively researched topic in evolutionary…