Research

Research, evidence gathering, literature, reports, investigation, and synthesis

skills in category: 21,402
pages available: 892

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse research skills

Showing 11,761–11,784 of 21,402 skills

Diffusing Blame Dale Principle Credit AssignmentAError Diffusion (ED) methodology for biologically plausible credit assignment under Dale's principle. Dual-stream excitatory/inhibitory architecture with modulo error routing. Achieves 96.7% MNIST and 61.7% CIFAR-10 under strict Dale's constraint. Integrates with PPO for RL. Trigger words: Dale's principle, error diffusion, excitatory-inhibitory, biologically plausible learning, credit assignment, dual-stream network.researchperformanceVotes: 0GitHub stars: 3
Differentiable Biophysical Simulation NeurostimulationADifferentiable biophysical simulation framework for inferring Hodgkin-Huxley parameters from extracellular MEA data. Enables rapid biophysical inference and precise neurostimulation prediction without invasive intracellular recordings.researchgotestingVotes: 0GitHub stars: 3
Dicke State Ansatz VqeAFeasibility-preserving mixed Dicke state ansatz for encoding equality and inequality constraints in variational quantum eigensolvers. Eliminates penalty terms by structurally encoding Hamming weight constraints into quantum circuits. Use when: (1) solving constrained combinatorial optimization with VQE/QAOA, (2) designing constraint-preserving ansatze, (3) eliminating penalty-based Lagrange multiplier tuning, (4) encoding equality/inequality constraints directly into quantum circuit structure...researchgoexpressVotes: 0GitHub stars: 3
Diagonal Ano QnnADiagonal Adaptive Non-local Observables (ANO) methodology for quantum neural networks — reduces observable parameter complexity from O(4^k) to O(2^k) while retaining full ANO expressivity via diagonal canonical representatives. For efficient VQA measurement design.researchpythongoVotes: 0GitHub stars: 3
Developmental Minimal Neural CircuitsADevelopmental neural circuit generation methodology from gene regulatory rules. Simulates cortical neurogenesis from single stem cell to generate domain-general topological substrates amenable to rapid learning. Use when studying developmental priors for neural network initialization, structural bias in neural architecture, or bio-inspired network topology generation.researchpythongoVotes: 0GitHub stars: 3
Surviving By Serving SbsASurviving by Serving (SBS) principle - functional relevance drives self-organization in complex adaptive systems with multi-agent resource transformationresearchpythongoVotes: 0GitHub stars: 3
Spikedyn A Framework For Energyefficient Spiking Neural Networks With Continual And Unsupervised Learning Capabilities In Dynamic EnvironmentsA**arXiv ID:** 2103.00424 **Authors:** Rachmad Vidya Wicaksana Putra, Muhammad Shafique **Published:** 2021-02-28T08:26:23Z **Abstract:** Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility, but their complexity still poses a serious research challenge to enable their energy-efficient design for resource-constrained scenarios (like embedded systems, IoT-Edge, etc.). We propose SpikeDyn, a compr...researchgoVotes: 0GitHub stars: 3
Spike Sparsity Edge Gpu DeploymentASpike sparsity vs deployed cost analysis for Variable Spiking Wavelet Neural Operator on edge GPU hardware. Activation: brain model, neural scaling, multimodal brain, fMRI, EEG, neural encoding.researchpythongoVotes: 0GitHub stars: 3
Spike Sparsity Deployment CostAAnalyzing deployment cost of spiking neural networks on edge hardware. Demonstrates that algorithmic spike sparsity may not translate to actual deployed cost reduction on commodity edge GPUs. Covers VS-WNO (Variable-Spiking Wavelet Neural Operator), WNO comparison, Jetson Orin Nano profiling. Activation: spike sparsity deployment, edge GPU SNN, neuromorphic deployment cost, VS-WNO, wavelet neural operator, SNN hardware, Jetson profiling.researchgoperformanceVotes: 0GitHub stars: 3
Recent Advances On Neural Network Pruning At InitializationA**arXiv ID:** 2103.06460 **Authors:** Huan Wang, Can Qin, Yue Bai, Yulun Zhang, Yun Fu **Published:** 2021-03-11T05:01:52Z **Abstract:** Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network. This paper offers the first survey concentrated on this emerging pruning fashion. We first introduce a generic formulation of neural network pruning...researchVotes: 0GitHub stars: 3
Orthogonal Residual QuantizationAOrthogonal Residual Projection (ORP) framework for multiplier-free Power-of-Two transformer quantization — replaces MAC operations with bit-shifts using dual-basis geometric projection, enabling efficient edge deployment of LLMs at sub-4-bit precision.researchpythongoVotes: 0GitHub stars: 3
Lance Low Rank Activation Compression For Efficient Ondevice Continual LearningA**arXiv ID:** 2509.21617 **Authors:** Marco Paul E. Apolinario, Kaushik Roy **Published:** 2025-09-25T21:33:40Z **Abstract:** On-device learning is essential for personalization, privacy, and long-term adaptation in resource-constrained environments. Achieving this requires efficient learning, both fine-tuning existing models and continually acquiring new tasks without catastrophic forgetting. Yet both settings are constrained by high memory cost of storing activations during backpropagation....researchgoVotes: 0GitHub stars: 3
Eoe Evolutionary Optimization Of Experts For Training Language ModelsA**arXiv ID:** 2509.24436 **Authors:** Yingshi Chen **Published:** 2025-09-29T08:18:26Z **Abstract:** This paper presents an evolutionary framework for the training of large language models(LLM). The models are divided into several experts(sub-networks), which have the same structure but different parameter values. Only one expert is trained at each step. After the classical AdamW optimization, some evolutionary operators(crossover, PSO, and mutation) act on the tensor weights between the curr...researchc++Votes: 0GitHub stars: 3
Comet Constraint Preserving QaoaAConstraint-preserving QAOA using XY-mixer for multiplex CRISPR gene editing optimization. Systematically compares structural constraint enforcement (XY-mixer) vs penalty-based approaches across simulator and real hardware. XY-mixer achieves >95% optimum probability by p=3 vs <6% for penalty variants. Activation: constraint-preserving QAOA, XY-mixer, CRISPR optimization, QUBO constraint enforcement, quantum gene editing, 约束保持QAOAresearchperformanceVotes: 0GitHub stars: 3
Coflow Scheduling Ocs NetworksAScheduling Coflows in Multi-Core Optical Circuit Switching Networks with Performance Guarantee. Optimize parallel data flow coordination in distributed systems using optical circuit switching.researchpythongoVotes: 0GitHub stars: 3
Arxiv 2608 18580v1 Facet Preserving Source Intent And Executable StatA**arXiv ID:** 2608.18580v1 **Authors:** Kou Shi, Zun Wang, Qisheng Su, Shiting Huang, Ziao Zhang, Zhen Fang, Qingnan Ren, Jin Liu, Yu Zeng, Yiming Zhao, Lin Chen, Zehui Chen, Feng Zhao **URL:** http://arxiv.org/abs/2608.18580v1 **Utility Score:** 1.00researchVotes: 0GitHub stars: 3
Density Matrix Propagation Qec DecodingAOptimal decoding methodology for quantum error correction using density matrix propagation through circuit-level noise. Enables ML-decoding benchmarking with pruning techniques and rigorous bounds for repetition codes and cellular automaton codes. Activation: density matrix propagation, optimal decoding, ML decoding, QEC benchmarking, BP+OSD accuracy, circuit-level noise decoding, quantum decoder benchmark, syndrome history propagation, pruning bounds, logical error rate, repetition code deco...researchgoperformanceVotes: 0GitHub stars: 3
Dendrocentric Snn Event ClassificationADendroNN dendrocentric neural network methodology for energy-efficient classification of event-based data. Incorporates dendritic computation principles into SNNs for improved spatiotemporal processing. Applies to: event-based vision, neuromorphic computing, dendritic computation, energy-efficient classification. Activation: dendrocentric neural, DendroNN, dendritic computation, event-based classification, dendrite-inspired SNN.researchgoVotes: 0GitHub stars: 3
Dendritic In Context Learning SnnADendritic In-Context Learning (DendriCL): a single-layer compartmental spiking neural network whose apical/dendritic subthreshold dynamics implement online Widrow-Hoff LMS, giving in-context learning without attention, depth, or inference-time synaptic plasticity. Activation: dendritic in-context learning, DendriCL, single-layer SNN ICL, compartmental spiking neuron, apical LMS dynamics, Garg-2022 ICL benchmark, biologically plausible in-context learning.researchgoapiVotes: 0GitHub stars: 3
Dendricl Icl Single Layer SnnADendriCL methodology for dendritic in-context learning in single-layer spiking neural networks. The apical compartment's subthreshold dynamics implement online Widrow-Hoff LMS, enabling general-purpose ICL without attention, depth, or inference-time plasticity. First SNN to solve Garg-2022 ICL benchmark at d≥30 where Transformers fail. Trigger: dendritic computation, in-context learning SNN, compartmental neuron, online LMS, biological ICL, neuromorphic ICL, apical dendrite, single-layer lear...researchgorailsVotes: 0GitHub stars: 3
Demented Brain Connectivity PatternsADifferential structural connectivity analysis in dementia and aging using the OASIS-3 dataset. Reveals both decreased connectivity (hippocampus, temporal lobe) and surprisingly increased connectivity (precuneus, cuneus, insula) in demented brains. Activation: dementia connectivity, brain network degradation, OASIS-3, structural connectivity aging, precuneus hyperconnectivity, demented brain.researchgitVotes: 0GitHub stars: 3
Decorrelation Grid Cell DistanceADistance coding via de-correlation of heterogeneous grid cell populations. Mathematical theory showing how small variability in grid properties enables distance encoding through population activity de-correlation, with non-intuitive 'sweet spot' predictions and range-distinguishability trade-offs. Activation: grid cells, distance coding, de-correlation, medial entorhinal cortex, navigation, population coding, heterogeneity, spatial navigation, place cells, path integrationresearchperformanceVotes: 0GitHub stars: 3
Decoded Quantum Interferometry BenchmarkAComplexity-theoretic benchmarking methodology for decoded quantum interferometry (DQI) and bounded-degree constraint satisfaction problems. Analyzes quantum advantage limits, classical vs quantum decoder performance, and approximation hardness over finite fields.researchpythongoVotes: 0GitHub stars: 3
Siren Signaware Recommendation Using Graph Neural NetworksA**arXiv ID:** 2108.08735 **Authors:** Changwon Seo, Kyeong-Joong Jeong, Sungsu Lim, Won-Yong Shin **Published:** 2021-08-19T15:07:06Z **Abstract:** In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy. However, such attempts have focused mostly on utilizing only the information of positive user-item interactions with high ratings. Thus, there is a challenge on...researchVotes: 0GitHub stars: 3