All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Been There Done That Metalearning With Episodic Recall**arXiv ID:** 1805.09692 **Authors:** Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew Botvinick **Published:** 2018-05-24T14:15:27Z **Abstract:** Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediate...Votes: 0GitHub stars: 3
- Beyond Backpropagation Monte Carlo Train Deep NetworksShows that simple Monte Carlo random mutation can train deep neural networks without gradients. No batch normalization or residual connections needed. Supports pure pruning training, discrete weights, and unconventional transfer functions. Demonstrated on 20+ layer networks and Transformer architectures. Use when working with gradient-free-training, monte-carlo-method, deep-neural-network-training.Votes: 0GitHub stars: 3
- Bounded Rational Decisionmaking In Feedforward Neural Networks**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...Votes: 0GitHub stars: 3
- Breaking The Conventional Forwardbackward Tie In Neural Networks Activation Functions**arXiv ID:** 2509.07236 **Authors:** Luigi Troiano, Francesco Gissi, Vincenzo Benedetto, Genny Tortora **Published:** 2025-09-08T21:30:00Z **Abstract:** Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to prevent flat gradient areas. This symmetry, linking forward activations closely to backward gradients, signif...Votes: 0GitHub stars: 3
- Challenging The Performanceinterpretability Tradeoff An Evaluation Of Interpretable Machine Learning Models**arXiv ID:** 2409.14429 **Authors:** Sven Kruschel, Nico Hambauer, Sven Weinzierl, Sandra Zilker, Mathias Kraus, Patrick Zschech **Published:** 2024-09-22T12:58:52Z **Abstract:** Machine learning is permeating every conceivable domain to promote data-driven decision support. The focus is often on advanced black-box models due to their assumed performance advantages, whereas interpretable models are often associated with inferior predictive qualities. More recently, however, a new generation ...Votes: 0GitHub stars: 3
- Classincremental Learning Based On Label Generation**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...Votes: 0GitHub stars: 3
- Code2lora Hypernetwork AdapterCode2LoRA: Hypernetwork-generated LoRA adapters for code language models under software evolution. Supports static and dynamic adaptation scenarios with zero inference overhead. Activation: code LLM adaptation, repository-specific LoRA, hypernetwork adapters, software evolution, code adaptation.Votes: 0GitHub stars: 3
- Codr Computation And Data Reuse Aware Cnn Accelerator**arXiv ID:** 2104.09798 **Authors:** Alireza Khadem, Haojie Ye, Trevor Mudge **Published:** 2021-04-20T07:20:17Z **Abstract:** Computation and Data Reuse is critical for the resource-limited Convolutional Neural Network (CNN) accelerators. This paper presents Universal Computation Reuse to exploit weight sparsity, repetition, and similarity simultaneously in a convolutional layer. Moreover, CoDR decreases the cost of weight memory access by proposing a customized Run-Length Encoding scheme a...Votes: 0GitHub stars: 3
- Cold Atom Reservoir ComputingCold-atom (neutral-atom) reservoir computing methodology for efficient machine learning tasks. Uses Rydberg atom arrays as physical reservoirs, encoding input data into Hamiltonian parameters and reading out via quantum measurements. Use when implementing reservoir computing on quantum hardware, exploring neutral-atom ML platforms, or building energy-efficient quantum-inspired classifiers. Triggers: cold atom reservoir, neutral atom computing, Rydberg reservoir, quantum reservoir machine, ato...Votes: 0GitHub stars: 3
- Collaborative Synthetic Data Generation For Knowledge Transfer In FederatedOne-shot federated learning (OSFL) addresses the communication overhead of federated learning by limiting training to a single round, but doing so without sacrificing model quality is non-trivial, par. Based on arXiv:2607.07565.Votes: 0GitHub stars: 3
- Compositional Density FusionCompositional 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...Votes: 0GitHub stars: 3
- Compositional Obverter Communication Learning From Raw Visual Input**arXiv ID:** 1804.02341 **Authors:** Edward Choi, Angeliki Lazaridou, Nando de Freitas **Published:** 2018-04-06T16:12:51Z **Abstract:** One of the distinguishing aspects of human language is its compositionality, which allows us to describe complex environments with limited vocabulary. Previously, it has been shown that neural network agents can learn to communicate in a highly structured, possibly compositional language based on disentangled input (e.g. hand- engineered features). Humans, ...Votes: 0GitHub stars: 3
- Cono Complex Neural Operator For Continous Dynamical Physical Systems**arXiv ID:** 2406.02597 **Authors:** Karn Tiwari, N M Anoop Krishnan, A P Prathosh **Published:** 2024-06-01T14:32:19Z **Abstract:** Neural operators extend data-driven models to map between infinite-dimensional functional spaces. While these operators perform effectively in either the time or frequency domain, their performance may be limited when applied to non-stationary spatial or temporal signals whose frequency characteristics change with time. Here, we introduce Complex Neural Operato...Votes: 0GitHub stars: 3
- Continuous Learning In Singleincrementaltask Scenarios**arXiv ID:** 1806.08568 **Authors:** Davide Maltoni, Vincenzo Lomonaco **Published:** 2018-06-22T09:22:42Z **Abstract:** It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single incremental task (e.g., class-incremental learning). In this p...Votes: 0GitHub stars: 3
- Convergent Representations Linguistic ConstructionsConvergent representations of linguistic constructions in human and artificial neural systems. Analyzes alignment between biological brain activity (EEG) and artificial neural language models (RNNs, Transformers) in processing Argument Structure Constructions. Activation: linguistic constructions, ASC, brain-language alignment, EEG language, construction grammar, convergent representations.Votes: 0GitHub stars: 3
- Convergent Representations Of Linguistic ConstructUnderstanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscience and linguistics. Recent computational studies show that artificial neural language model...Votes: 0GitHub stars: 3
- Convolutional Neural Network Adversarial Autoencoder... Activation: EEG, brain signal, electroencephalography, brain network, graph, connectivityVotes: 0GitHub stars: 3
- Convolutional Neural Network AdversarialConvolutional Neural Network and Adversarial Autoencoder in EEG images classification... Activation: adversarial, 脑电图, 对抗, eeg, 脑Votes: 0GitHub stars: 3
- Cosco A Sharpnessaware Training Framework For Fewshot Multivariate Time Series Classification**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. ...Votes: 0GitHub stars: 3
- Cosinegate Semantic Dynamic Routing Via Cosine Incompatibility In Residual Networks**arXiv ID:** 2512.22206 **Authors:** Yogeswar Reddy Thota **Published:** 2025-12-21T18:26:18Z **Abstract:** Modern deep residual networks perform substantial redundant computation by evaluating all residual blocks for every input, even when identity mappings suffice. We introduce CosineGate, an end-to-end differentiable architecture for dynamic routing in residual networks that uses cosine incompatibility between identity and residual feature representations as a self-supervised skip signal....Votes: 0GitHub stars: 3
- Deep Learning Closed Loop Tms BciDeep learning in brain-computer interfaces with closed-loop transcranial magnetic stimulation. Combines real-time EEG processing with adaptive TMS for neurological therapy. (arXiv:2604.11608, 2026-04-12)Votes: 0GitHub stars: 3
- Deep Learning Generalizes Because The Parameterfunction Map Is Biased Towards Simple Functions**arXiv ID:** 1805.08522 **Authors:** Guillermo Valle-Pérez, Chico Q. Camargo, Ard A. Louis **Published:** 2018-05-22T11:51:36Z **Abstract:** Deep neural networks (DNNs) generalize remarkably well without explicit regularization even in the strongly over-parametrized regime where classical learning theory would instead predict that they would severely overfit. While many proposals for some kind of implicit regularization have been made to rationalise this success, there is no consensus for th...Votes: 0GitHub stars: 3
- Deep Learning Mental Rotation VrMechanistic model of human mental rotation combining equivariant neural encoder, neuro-symbolic object encoder, and VR experiments for validationVotes: 0GitHub stars: 3
- Deep Metric Learning Improves Lab Of Origin Prediction Of Genetically Engineered Plasmids**arXiv ID:** 2111.12606 **Authors:** Igor M. Soares, Fernando H. F. Camargo, Adriano Marques, Oliver M. Crook **Published:** 2021-11-24T16:29:03Z **Abstract:** Genome engineering is undergoing unprecedented development and is now becoming widely available. To ensure responsible biotechnology innovation and to reduce misuse of engineered DNA sequences, it is vital to develop tools to identify the lab-of-origin of engineered plasmids. Genetic engineering attribution (GEA), the ability to make ...Votes: 0GitHub stars: 3
- Deep Neural Network Guided Pso Tracking GlobalDeep Neural Network-guided Particle Swarm Optimization for tracking global optima in complex dynamic environments. Uses DNN as surrogate model to predict promising search regions, accelerating PSO convergence while maintaining tracking of moving optima. Activation: PSO, particle swarm optimization, DNN-guided search, global optimization, surrogate modelVotes: 0GitHub stars: 3
- Deep Tracking Seeing Beyond Seeing Using Recurrent Neural Networks**arXiv ID:** 1602.00991 **Authors:** Peter Ondruska, Ingmar Posner **Published:** 2016-02-02T16:10:16Z **Abstract:** This paper presents to the best of our knowledge the first end-to-end object tracking approach which directly maps from raw sensor input to object tracks in sensor space without requiring any feature engineering or system identification in the form of plant or sensor models. Specifically, our system accepts a stream of raw sensor data at one end and, in real-time, produces an ...Votes: 0GitHub stars: 3
- Democratic Icai Steering From PreferencesDemocratic Inverse Constitutional AI (ICAI) methodology that derives steering principles from human preferences through structured debate, capturing the reasoning underlying human judgments rather than just final choices.Votes: 0GitHub stars: 3
- Demopsd Policy Self DistillationDisagreement-Modulated Policy Self-Distillation framework for LLM reasoning. Resolves privileged information leakage and exploration preservation in on-policy distillation via reverse-KL barycenter target, achieving leakage attenuation and exploration preservation simultaneously.Votes: 0GitHub stars: 3
- Dias A Domainindependent Alifebased Problemsolving System**arXiv ID:** 2203.06855 **Authors:** Babak Hodjat, Hormoz Shahrzad, Risto Miikkulainen **Published:** 2022-03-14T04:53:26Z **Abstract:** A domain-independent problem-solving system based on principles of Artificial Life is introduced. In this system, DIAS, the input and output dimensions of the domain are laid out in a spatial medium. A population of actors, each seeing only part of this medium, solves problems collectively in it. The process is independent of the domain and can be implement...Votes: 0GitHub stars: 3
- Direct On Policy DistillationWeak-to-strong generalization methodology transferring RL-induced policy shifts as dense implicit reward signals from smaller to larger models, enabling cross-scale RL outcome reuse.Votes: 0GitHub stars: 3
- Discovering Adaptable Symbolic Algorithms From Scratch**arXiv ID:** 2307.16890 **Authors:** Stephen Kelly, Daniel S. Park, Xingyou Song, Mitchell McIntire, Pranav Nashikkar, Ritam Guha, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu Naresh Boddeti, Jie Tan, Esteban Real **Published:** 2023-07-31T17:57:48Z **Abstract:** Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero (ARZ), a method based on AutoML-Zero that discovers zero-shot adaptable polici...Votes: 0GitHub stars: 3
- Distilling Optimal Neural Networks Rapid Search In Diverse Spaces**arXiv ID:** 2012.08859 **Authors:** Bert Moons, Parham Noorzad, Andrii Skliar, Giovanni Mariani, Dushyant Mehta, Chris Lott, Tijmen Blankevoort **Published:** 2020-12-16T11:00:19Z **Abstract:** Current state-of-the-art Neural Architecture Search (NAS) methods neither efficiently scale to multiple hardware platforms, nor handle diverse architectural search-spaces. To remedy this, we present DONNA (Distilling Optimal Neural Network Architectures), a novel pipeline for rapid, scalable and dive...Votes: 0GitHub stars: 3
- Distinction Maximization Loss Efficiently Improving Outofdistribution Detection And Uncertainty Estimation By Replacing The Loss And Calibrating**arXiv ID:** 2205.05874 **Authors:** David Macêdo, Cleber Zanchettin, Teresa Ludermir **Published:** 2022-05-12T04:37:35Z **Abstract:** Building robust deterministic neural networks remains a challenge. On the one hand, some approaches improve out-of-distribution detection at the cost of reducing classification accuracy in some situations. On the other hand, some methods simultaneously increase classification accuracy, uncertainty estimation, and out-of-distribution detection at the expense ...Votes: 0GitHub stars: 3
- Distributional Matrix CompletionDistributional matrix completion methodology using kernel mean embeddings and Tucker rank for probability-distribution-valued matrices. Represents each matrix entry as a probability distribution via RKHS embeddings, introduces functional unfolding operators to bridge infinite-dimensional embeddings with finite-dimensional tensor structure. Applicable to statistical learning with distributional data, quantum state tomography, financial risk modeling.Votes: 0GitHub stars: 3
- Domain Generalization Through Metalearning A Survey**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...Votes: 0GitHub stars: 3
- Double Preconditioning Test Time OptimizationDouble Preconditioning (DoPr) optimization paradigm combining gradient-wise preconditioning (Adam/Muon) with activation-wise preconditioning (KFAC) to improve test-time performance in settings with train-test feedback mismatch. Addresses error accumulation in autoregressive language modeling, flow-based generative modeling, and robot policy learning. Drop-in intervention for TTF settings where validation loss doesn't reflect downstream metrics. Activation: test-time feedback, double precondit...Votes: 0GitHub stars: 3
- Dynamic Mean Field Nonlinear Noise Recurrent NetworksSkill for dynamic mean field nonlinear noise recurrent networksVotes: 0GitHub stars: 3
- Dynamicsaware Qualitydiversity For Efficient Learning Of Skill Repertoires**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...Votes: 0GitHub stars: 3
- Effective Model Sparsification By Scheduled Growandprune Methods**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...Votes: 0GitHub stars: 3
- Effective Rank Qnn ExpressivityMethodology for measuring and maximizing Quantum Neural Network (QNN) expressivity using effective rank (kappa). Introduces a quantitative measure capturing the number of effectively independent variational parameters in parameterized quantum circuits. Use when: designing QNN architectures, analyzing barren plateaus, optimizing variational quantum circuits, measuring quantum model capacity, or studying expressivity-entanglement relationships. Triggered by: QNN expressivity, effective rank qua...Votes: 0GitHub stars: 3
- Efficient Coding Criticality SloppinessEfficient coding under resource constraints drives neural systems towards criticality and sloppiness — a unified theoretical framework linking Fisher information maximization to critical brain dynamics.Votes: 0GitHub stars: 3
- Elastic Graph Neural Networks**arXiv ID:** 2107.06996 **Authors:** Xiaorui Liu, Wei Jin, Yao Ma, Yaxin Li, Hua Liu, Yiqi Wang, Ming Yan, Jiliang Tang **Published:** 2021-07-05T01:36:01Z **Abstract:** While many existing graph neural networks (GNNs) have been proven to perform $\ell_2$-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via $\ell_1$-based graph smoothing. As a result, we introduce a family of GNNs (Elastic GNNs) based on $...Votes: 0GitHub stars: 3
- Empirical Investigation Into Configuring Echo State Networks For Representative Benchmark Problem Domains**arXiv ID:** 2508.10887 **Authors:** Brooke R. Weborg, Gursel Serpen **Published:** 2025-08-14T17:55:47Z **Abstract:** This paper examines Echo State Network, a reservoir computer, performance using four different benchmark problems, then proposes heuristics or rules of thumb for configuring the architecture, as well as the selection of parameters and their values, which are applicable to problems within the same domain, to help serve to fill the experience gap needed by those entering this ...Votes: 0GitHub stars: 3
- Energy Based Dynamical Models Neurocomputation LearningRecent advances at the intersection of control theory, neuroscience, and machine learning have revealed novel mechanisms by which dynamical systems perform computation. These advances encompass a wide. Activation: energy-based models, dynamical systems, ODE complexityVotes: 0GitHub stars: 3
- Energy Based TransformersResearch 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.Votes: 0GitHub stars: 3
- Enhancing Onceforall A Study On Parallel Blocks Skip Connections And Early Exits**arXiv ID:** 2302.01888 **Authors:** Simone Sarti, Eugenio Lomurno, Andrea Falanti, Matteo Matteucci **Published:** 2023-02-03T17:53:40Z **Abstract:** The use of Neural Architecture Search (NAS) techniques to automate the design of neural networks has become increasingly popular in recent years. The proliferation of devices with different hardware characteristics using such neural networks, as well as the need to reduce the power consumption for their search, has led to the realisation of On...Votes: 0GitHub stars: 3
- Evaluating Encoding Strategies Biological Neural NetworksSkill for understanding and applying the research from arXiv:2607.13644 "Evaluating Encoding Strategies for Closed-Loop Classification in Biological Neural Networks"Votes: 0GitHub stars: 3
- Ever Evolving Evaluator Ev3 Towards Flexible And Reliable Metaoptimization For Knowledge Distillation**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...Votes: 0GitHub stars: 3
- Evolutionary Augmentation Policy Optimization For Selfsupervised Learning**arXiv ID:** 2303.01584 **Authors:** Noah Barrett, Zahra Sadeghi, Stan Matwin **Published:** 2023-03-02T21:16:53Z **Abstract:** Self-supervised Learning (SSL) is a machine learning algorithm for pretraining Deep Neural Networks (DNNs) without requiring manually labeled data. The central idea of this learning technique is based on an auxiliary stage aka pretext task in which labeled data are created automatically through data augmentation and exploited for pretraining the DNN. However, the ef...Votes: 0GitHub stars: 3
- Evolutionary Data Measures Understanding The Difficulty Of Text Classification Tasks**arXiv ID:** 1811.01910 **Authors:** Edward Collins, Nikolai Rozanov, Bingbing Zhang **Published:** 2018-11-05T18:39:54Z **Abstract:** Classification tasks are usually analysed and improved through new model architectures or hyperparameter optimisation but the underlying properties of datasets are discovered on an ad-hoc basis as errors occur. However, understanding the properties of the data is crucial in perfecting models. In this paper we analyse exactly which characteristics of a dataset...Votes: 0GitHub stars: 3