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 11,641–11,664 of 21,402 skills

Geosd Geometric Self DistillationAGeometric Self-Distillation (GeoSD) methodology for preserving OOD generalization during privileged-context self-distillation. Uses Hellinger loss and Fisher-Rao proximal term to prevent drift in predictive behavior.researchpythongitVotes: 0GitHub stars: 3
Frozen Lgp QaoaAFrozenLGP adaptive decomposition framework for divide-and-conquer QAOA. Transforms partitionability from an assumption into an enforceable property by freezing obstructing vertices and folding their energy into linear bias terms. Enables 100% decomposition coverage on graphs up to 10,000 vertices including dense/high-connectivity instances. Activation: FrozenLGP, divide-and-conquer QAOA, qubit freezing, graph partitioning QAOA, adaptive decomposition, max-flow vertex cut, dense graph QAOAresearchgoperformanceVotes: 0GitHub stars: 3
Forgetfree Continual Learning With Softwinning SubnetworksA**arXiv ID:** 2303.14962 **Authors:** Haeyong Kang, Jaehong Yoon, Sultan Rizky Madjid, Sung Ju Hwang, Chang D. Yoo **Published:** 2023-03-27T07:53:23Z **Abstract:** Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which states that competitive smooth (non-binary) subnetworks exist within a dense network in continual learning tasks, we investigate two proposed architecture-based continual learning methods which sequentially learn and select adaptive binary- (WSN) and non-binary Soft-S...researchgitVotes: 0GitHub stars: 3
Experiments On Properties Of Hidden Structures Of Sparse Neural NetworksA**arXiv ID:** 2107.12917 **Authors:** Julian Stier, Harshil Darji, Michael Granitzer **Published:** 2021-07-27T16:18:13Z **Abstract:** Sparsity in the structure of Neural Networks can lead to less energy consumption, less memory usage, faster computation times on convenient hardware, and automated machine learning. If sparsity gives rise to certain kinds of structure, it can explain automatically obtained features during learning. We provide insights into experiments in which we show how spar...researchperformanceVotes: 0GitHub stars: 3
Evolutionary Hyperparameter Optimization To Find LADerived from arXiv:2606.29684 - Evolutionary Hyperparameter Optimization to Find Lightweight CNN Models for Autonomous SteeringresearchgoVotes: 0GitHub stars: 3
Evolutionary Echo State Network Evolving Reservoirs In The Fourier SpaceA**arXiv ID:** 2206.04951 **Authors:** Sebastian Basterrech, Gerardo Rubino **Published:** 2022-06-10T08:59:40Z **Abstract:** The Echo State Network (ESN) is a class of Recurrent Neural Network with a large number of hidden-hidden weights (in the so-called reservoir). Canonical ESN and its variations have recently received significant attention due to their remarkable success in the modeling of non-linear dynamical systems. The reservoir is randomly connected with fixed weights that don't chan...researchgoperformanceVotes: 0GitHub stars: 3
Ever Evolving Evaluator Ev3 Towards Flexible And Reliable Metaoptimization For Knowledge DistillationA**arXiv ID:** 2310.18893 **Authors:** Li Ding, Masrour Zoghi, Guy Tennenholtz, Maryam Karimzadehgan **Published:** 2023-10-29T04:00:33Z **Abstract:** We introduce EV3, a novel meta-optimization framework designed to efficiently train scalable machine learning models through an intuitive explore-assess-adapt protocol. In each iteration of EV3, we explore various model parameter updates, assess them using pertinent evaluation methods, and then adapt the model based on the optimal updates and pr...researchgogitVotes: 0GitHub stars: 3
Energy Based TransformersAResearch paper: Energy-Based Transformers are Scalable Learners and Thinkers. Introduces EBTs - a new class of Energy-Based Models that scale 35% faster than Transformer++ and improve System 2 Thinking by 29% through gradient descent-based energy minimization.researchgoawsVotes: 0GitHub stars: 3
Efficient Coding Criticality SloppinessAEfficient coding under resource constraints drives neural systems towards criticality and sloppiness — a unified theoretical framework linking Fisher information maximization to critical brain dynamics.researchgoawsVotes: 0GitHub stars: 3
Effective Model Sparsification By Scheduled Growandprune MethodsA**arXiv ID:** 2106.09857 **Authors:** Xiaolong Ma, Minghai Qin, Fei Sun, Zejiang Hou, Kun Yuan, Yi Xu, Yanzhi Wang, Yen-Kuang Chen, Rong Jin, Yuan Xie **Published:** 2021-06-18T01:03:13Z **Abstract:** Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation results in long inference time. Model sparsification can reduce the computation and memory cost while maintaining model...researchgogitVotes: 0GitHub stars: 3
Dynamicsaware Qualitydiversity For Efficient Learning Of Skill RepertoiresA**arXiv ID:** 2109.08522 **Authors:** Bryan Lim, Luca Grillotti, Lorenzo Bernasconi, Antoine Cully **Published:** 2021-09-16T08:35:35Z **Abstract:** Quality-Diversity (QD) algorithms are powerful exploration algorithms that allow robots to discover large repertoires of diverse and high-performing skills. However, QD algorithms are sample inefficient and require millions of evaluations. In this paper, we propose Dynamics-Aware Quality-Diversity (DA-QD), a framework to improve the sample effici...researchgoVotes: 0GitHub stars: 3
Domain Generalization Through Metalearning A SurveyA**arXiv ID:** 2404.02785 **Authors:** Arsham Gholamzadeh Khoee, Yinan Yu, Robert Feldt **Published:** 2024-04-03T14:55:17Z **Abstract:** Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack performance when faced with out-of-distribution (OOD) data, a common scenario due to the inevitable domain shifts in real-world applications. This limitation stems from the common assumption that training and testing data share the same distribution--an assumption frequent...researchgotestingVotes: 0GitHub stars: 3
Deep Learning Mental Rotation VrAMechanistic model of human mental rotation combining equivariant neural encoder, neuro-symbolic object encoder, and VR experiments for validationresearchgotestingVotes: 0GitHub stars: 3
Cosco A Sharpnessaware Training Framework For Fewshot Multivariate Time Series ClassificationA**arXiv ID:** 2409.09645 **Authors:** Jesus Barreda, Ashley Gomez, Ruben Puga, Kaixiong Zhou, Li Zhang **Published:** 2024-09-15T07:41:55Z **Abstract:** Multivariate time series classification is an important task with widespread domains of applications. Recently, deep neural networks (DNN) have achieved state-of-the-art performance in time series classification. However, they often require large expert-labeled training datasets which can be infeasible in practice. In few-shot settings, i.e. ...researchgotestingVotes: 0GitHub stars: 3
Convergent Representations Of Linguistic ConstructAUnderstanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscience and linguistics. Recent computational studies show that artificial neural language model...researchgoVotes: 0GitHub stars: 3
Compositional Density FusionACompositional boundaries for density fusion methodology from arXiv:2606.05871 — algebraic compositionality analysis for hierarchical probabilistic model fusion. Characterizes normalized weighted linear pooling as the unique order-invariant fusion rule and shows why pairwise solvability alone is insufficient for schedule-independent distributed uncertainty management. Activation: density fusion, uncertainty management, order-invariant fusion, distributed probabilistic models, compositional fus...researchpythonnodeVotes: 0GitHub stars: 3
Classincremental Learning Based On Label GenerationA**arXiv ID:** 2306.12619 **Authors:** Yijia Shao, Yiduo Guo, Dongyan Zhao, Bing Liu **Published:** 2023-06-22T01:14:47Z **Abstract:** Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF). This paper reports our finding that if we formulate CIL as a continual label generation problem, CF is drastically reduced and the generaliz...researchVotes: 0GitHub stars: 3
Bounded Rational Decisionmaking In Feedforward Neural NetworksA**arXiv ID:** 1602.08332 **Authors:** Felix Leibfried, Daniel Alexander Braun **Published:** 2016-02-26T14:15:03Z **Abstract:** Bounded rational decision-makers transform sensory input into motor output under limited computational resources. Mathematically, such decision-makers can be modeled as information-theoretic channels with limited transmission rate. Here, we apply this formalism for the first time to multilayer feedforward neural networks. We derive synaptic weight update rules for tw...researchgitVotes: 0GitHub stars: 3
Bacterial Reservoir ComputingABacterial metabolic models as physical reservoirs for computation. dFBA simulations of microbial growth curves as reservoir states. Separability and similarity metrics predict performance. Activation: reservoir computing, bacterial model, biological computation, dFBA.researchpythongoVotes: 0GitHub stars: 3
Arxiv 2609 10092v1 Rap Research Attention Prediction Reveals Target CA**arXiv ID:** 2609.10092v1 **Authors:** Yingqian Wu, Jingcong Liang, Siyuan Wang, Zhenfei Yin, Philip Torr, Junchi Yu, Zhongyu Wei **URL:** http://arxiv.org/abs/2609.10092v1 **Utility Score:** 1.00researchVotes: 0GitHub stars: 3
Arxiv 2608 25592v1 A Hierarchical Synergistic Deep Learning FrameworkA**arXiv ID:** 2608.25592v1 **Authors:** Hongwei Du, Dingyang Lv, Baole Wei, Yongheng Li, Feng Yu, Ziheng Lu, Siqi Shi, Hong Wang **URL:** http://arxiv.org/abs/2608.25592v1 **Utility Score:** 1.00researchVotes: 0GitHub stars: 3
Arxiv 2608 25481v1 Synthesis Of Hopfield Neural Network Novel ResultsA**arXiv ID:** 2608.25481v1 **Authors:** Garimella Rama Murthy **URL:** http://arxiv.org/abs/2608.25481v1 **Utility Score:** 1.00researchVotes: 0GitHub stars: 3
Arxiv 2608 22746v1 Generative Neural Networks For Sinkhorn DistributiA**arXiv ID:** 2608.22746v1 **Authors:** Fenglin Zhang, Teyan Liu, Jie Wang **URL:** http://arxiv.org/abs/2608.22746v1 **Utility Score:** 1.00researchtestingVotes: 0GitHub stars: 3
Arxiv 2608 20104 Structured Affinity For Unsupervised Visual ClassAStructured Affinity for Unsupervised Visual Class-Incremental Memory in Deep Artificial Immune Networks (arXiv: 2608.20104)researchgogitVotes: 0GitHub stars: 3