61 papers
This paper challenges the prevailing assumption of Spiking Neural Networks' inherent energy superiority by introducing a rigorous, fair-comparison framework that reveals SNNs only outperform Quantized ANNs under specific low-spike-rate conditions, while demonstrating that such optimized SNNs could nearly double the battery life of devices like smartwatches.
This study compares a transparent ANFIS-FBCSP-PSO model with the deep-learning benchmark EEGNet on motor imagery EEG data, revealing that the fuzzy-neural approach offers superior within-subject performance and interpretability while EEGNet demonstrates stronger cross-subject generalization, thereby providing practical guidance for selecting BCI systems based on specific design priorities.
This paper presents a white-box support vector machine framework optimized by five meta-heuristic swarm algorithms to monitor the health of toothed milling cutters in real-time by characterizing spindle vibrations and selecting relevant statistical features through Recursive Feature Elimination with Cross-Validation.
This paper introduces PolarBear, a Bayesian racing framework that identifies Pareto-optimal anytime algorithms by adaptively sampling temporal Plackett-Luce rankings to eliminate dominated candidates without requiring objective bounds, normalization, or known optima.
RECAP is a bio-inspired image classification method that couples untrained reservoir dynamics with a self-organizing Hebbian prototype readout to achieve robust, backpropagation-free learning capable of generalizing to corrupted inputs without prior exposure.
The paper introduces OptiRoulette, a stochastic meta-optimizer that dynamically selects update rules from a pool during training, demonstrating significantly faster convergence and higher test accuracy across multiple image-classification benchmarks compared to a standard AdamW baseline.
This paper presents a fully integrated, event-driven e-skin system featuring a 16x16 piezoresistive array and a dynamic binary scanning strategy that achieves significant data compression and efficiency gains while maintaining 92.11% accuracy in real-time handwritten digit recognition via an FPGA-based spiking neural network.
The paper introduces GOT-JEPA, a model-predictive pretraining framework that enhances generic object tracking generalization by predicting tracking models from corrupted frames, and further proposes OccuSolver to refine occlusion handling through iterative visibility estimation and point-centric tracking.
This survey provides a comprehensive overview of differential privacy in machine learning, tracing its evolution from foundational definitions to its integration with modern models like LLMs, while examining practical methods for preserving privacy and evaluating their effectiveness.
This paper proposes SwitchMT, a novel methodology that utilizes Deep Spiking Q-Networks with active dendrites and an adaptive task-switching policy to effectively mitigate task interference and enable scalable, energy-efficient multi-task learning for resource-constrained autonomous agents.
This paper introduces COMIC, a fully automated AI system that utilizes a multi-agent framework with LLM critics trained on YouTube data to iteratively generate high-quality, diverse comedic videos comparable to professional sketch shows.
This paper demonstrates that a natively spiking neuromorphic algorithm for solving partial differential equations possesses intrinsic fault tolerance, maintaining accuracy even when up to 32% of neurons and 90% of spikes are dropped, with this robustness being tunable via structural hyperparameters.
This paper introduces a physiology-informed reinforcement learning framework that utilizes low-dimensional muscle synergies as a control constraint to significantly enhance the biomechanical fidelity and generalization of predictive musculoskeletal simulations across diverse locomotion conditions.
This paper introduces ForwardFlow, a deep learning framework that employs a branched summary network to solve frequentist parameter estimation problems in simulation-only settings, demonstrating properties like finite sample exactness and robustness while automatically approximating complex algorithms such as the EM-algorithm.
The paper introduces Panda, a pretrained foundation model for chaotic dynamics that, despite being trained exclusively on synthetic low-dimensional ordinary differential equations, demonstrates emergent zero-shot forecasting capabilities for unseen chaotic systems, real-world experimental data, and even partial differential equations.
This paper proposes a lightweight hybrid framework for the Game of the Amazons that integrates Graph Attention Autoencoders, Stochastic Graph Genetic Algorithms, and GPT-4o-mini to overcome resource constraints, achieving decision accuracy improvements of 15%–56% over baselines and outperforming its teacher model by effectively denoising LLM outputs through structural graph reasoning.
This paper proposes a bio-inspired, digital pheromone-based framework that mimics ant colony behavior to dynamically classify industrial production lines as In-Control or Out-of-Control and forecast maintenance needs by aggregating real-time temperature data, threat signals, and decaying environmental scores into a single adaptive indicator.
This paper introduces TT-SNN, a novel framework that leverages Tensor Train decomposition and a parallel computation pipeline to significantly reduce the parameter size, computational cost, and energy consumption of Spiking Neural Networks during training while maintaining accuracy on both static and dynamic datasets.
The paper proposes D2MOE, a novel framework that integrates dual-view multiscale feature extraction with a multi-objective evolutionary algorithm to automatically discover optimal fusion architectures, thereby significantly improving the accuracy and efficiency of protein intrinsic disorder prediction compared to existing state-of-the-art methods.
This paper provides a comprehensive review and formal specification of Predictive Coding Networks (PCNs), highlighting their biological plausibility, computational efficiency through inference learning, and versatility as a probabilistic framework that extends beyond traditional backpropagation-based neural networks.