Mnist

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 40

All topics

Neural scaling laws and evolution of learnable activation functions of Kolmogorov-Arnold networks
Oct 1, 2026Tilen Cadez, Sanghoon Lee, Kyoung-Min KimKolmogorov-Arnold Networks Scaling Laws
Asia Pacific Center for Theoretical Physics, Pohang, Gyeongbuk, 37673, Republic of Korea · Department of Physics, Pohang University of Science and Technology, Pohang, Gyeongbuk 37673, Republic of Korea
Beyond Affine Transformations: A Soft Dominance Layer for Coordinate-Wise Neural Computation
Sep 30, 2026Mariano RiveraAffine Mnist
Centro de Investigación en Matemáticas, A.C. Guanajuato, 36023, México
Diffusion Models and Concept Formation
Sep 11, 2026Zekun Wang, Karthik Singaravadivelan, Christopher J. MacLellanDiffusion Models Hierarchical
College of Computing, Georgia Institute of Technology, Atlanta, GA 30332 USA
Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution
Sep 10, 2026Romain Claret, Arthur Gygax, Michael O'Neill +3Neuroevolution Mnist
University of Neuchâtel, Neuchâtel, Switzerland · University College Dublin, Ireland
Spectral characteristics of autoencoder parameters as a vector representation of data
Sep 3, 2026Maria Nikitina, Anton Bishuk, Oleg BakhteevAutoencoder Architectures Mnist
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
Aug 31, 2026Vernon Toh, Navonil Majumder, Zhengyuan Liu +2Perceptually Artificial Intelligence Agents
DeCLaRe Lab, Nanyang Technological University, Singapore · Agency for Science, Technology, and Research (A*STAR), Singapore
Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$
Aug 13, 2026Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho +1Ontology Efficient Latent Reasoning
Computer Science Program, Computer, Electrical, and Mathematical Sciences & Engineering Division, King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia
eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion Models
Aug 9, 2026Ignacio Bugueno-Cordova, Fabian Valderrama, Rodrigo VerschaeImage Reconstruction Diffusion Models
Institute of Engineering Sciences, Universidad de OHiggins, Rancagua, Chile · The Iniciativa de Datos e Inteligencia Artificial, University of Chile, Santiago, Chile
Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework
Jul 28, 2026Zeki Doruk ErdenReplay-Based Continual Learning Multiscale
Sabanci University, Istanbul, Turkey
AI-interpreted Optical Scattering for Robust and Focal Depth-Aware Imaging
Jul 24, 2026Eunji Ko, Patrick Ross, Corey Hart +1Image Reconstruction Speckle
University of Maryland – College Park · Lockheed Martin
Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training
Jul 17, 2026Anxhelo Shehu, Enes Stastoli, Arben CelaResnet-18 Convolutional Neural Networks
AI Laboratory, University Metropolitan Tirana, Tirana, Albania. · Laboratory of Images Signals and Intelligent Systems, ESIEE Paris, Paris, France.
Learning from Noise: Effective-Rank Collapse and Out-of-Distribution Rejection in Restricted Boltzmann Machines
Jul 11, 2026Oshada Rathnayake, Nikhil ShuklaOut-Of-Distribution Low-Rank Structure
University of Virginia, Charlottesville, VA, 22903, USA
Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks
Jul 10, 2026Wout Mommen, Lars Keuninckx, Matthias Hartmann +2Differentiable Logic Gate Networks Mnist
imec, Kapeldreef 75, Leuven, 3001, , Belgium · Vrije Universiteit Brussel, Peinlaan 2, Elsene, 1050, , Belgium
Beyond Backpropagation: Monte Carlo Method Can Train Deep Neural Networks
Jul 9, 2026Hong ZhaoBackpropagation Gradient-Based Optimization
Department of Physics, Xiamen University, Xiamen 361005, China · Lanzhou Center for Theoretical Physics, Lanzhou University, Lanzhou 730000, China
Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
Jul 9, 2026Jakob Suchan, Julius Monsen, Salim Baloch +1Answer Set Programming Neuro-Symbolic Framework
Constructor University Bremen, Bremen, Germany · CoDesign Lab > Cognitive Vision · Örebro University, Örebro, Sweden
Unraveling Machine Behavior by Multi-Level Bias Analysis and Detection: Methodology and Application to Computer Vision
Jul 8, 2026Ignacio Serna, Aythami Morales, Julian FierrezMnist Computer Vision
Center for Humans and Machines, Max Planck Institute for Human Development, Berlin, Germany · BiometricsAI, UAM, Madrid, Spain · Department of Mathematics, ULPGC, Spain
How Far is Too Far? Defining the Distance Threshold for Verification Siamese Networks
Jul 6, 2026Heloísa Dias Viotto, Cauê Samonek, Lucas Garcia Pedroso +3Distance Mnist
∗Departamento de Informática (DInf), Universidade Federal do Paraná, Curitiba, PR - Brazil · † Departamento de Matemática (DMAT), Universidade Federal do Paraná Curitiba, PR - Brazil
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
Jul 6, 2026Benjamin Ballyk, Teyun Kwon, Miran Özdogan +1Speech Enhancement Auditory Attention
PNPL Department of Engineering Science University of Oxford
Machine-learnable Sets
Jun 27, 2026Veit Elser, Manish Krishan LalLearnability Mnist
Department of Physics, Cornell · Mathematics, Independent Researcher, India
One-Shot Data Selection for Medical Image Classification via Graph Coverage
Jun 20, 2026Zahiriddin Rustamov, Nadia Badawi, Rafat Damseh +1Medical Image Classification Label Propagation
Department of Computer Science and Software Engineering, United Arab Emirates University, Al Ain, United Arab Emirates
GrapNet: A Programmable Dynamic-Architecture Neural Graph Substrate
Jun 17, 2026Zirong LiGraph Neural Networks Mnist
Tiangong University
A homotopy-type-theoretic generalization of neurosymbolic inference
Jun 16, 2026Fernando Zhapa-Camacho, Robert HoehndorfNeuro-Symbolic Framework Neuroflex
Computer, Electrical and Mathematical Sciences & Engineering Division, King Abdullah University of Science and Technology, 4700 KAUST, 23955, Thuwal, Saudi Arabia · KAUST Center of Excellence for Smart Health (KCSH) · KAUST Center of Excellence for Generative AI
Robustness Verification of Recurrent Neural Networks with Abstraction Refinement
Jun 10, 2026Li-Jen Lin, Chih-Duo HongNeural Network Verification Recurrent Neural Networks
Dept. of Management Information Systems National Chengchi University Taipei, Taiwan
BRo-JEPA: Learning Modular Arithmetic in Latent Space
May 31, 2026Divyansh Jha, Yuanfang Xie, Varan Mehra +1Latent World Models Mnist
1Georgia Institute of Technology · 2NYU Langone Health
Learning Compositional Latent Structure with Vector Networks
May 27, 2026Niclas Pokel, Benjamin F. GreweNetwork Science Mnist
Institute of Neuroinformatics, UZH / ETH Zurich ETH AI Center Zurich, Switzerland
Do We Really Need Quantum Machine Learning?: A Multidimensional Empirical Study
May 27, 2026Sudip Vhaduri, Ryan Gammon, Sayanton DibboQuantum Machine Learning Quantum Kernels
Department of Computer Science, University of Alabama, AL 35487 · Clemson University
Optimizing Multidimensional Scaling in Gini Metric Spaces
May 24, 2026Cassandra Mussard, Stéphane MussardMetric Spaces Gaussian Mixture Models
CESBIO, Univ. Toulouse Toulouse, France · CHROME, Univ. Nˆımes UM6P, AIRESS Nˆımes, France
FQPDR: Federated Quantum Neural Network for Privacy-preserving Early Detection of Diabetic Retinopathy
May 8, 2026Debashis De, Mahua Nandy Pal, Dipankar HazraQuantum Neural Networks Federated Learning
Department of Computer Science and Engineering, Maulana Abul Kalam Azad University of Technology, West Bengal · Department of Computer Science and Engineering, MCKV Institute of Engineering, West Bengal · Department of Computer Science and Engineering, OmDayal Group of Institutions, West Bengal
The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
May 7, 2026Flavio Nicoletti, Chenxiao Ma, Enrico Ventura +2Score-Based Diffusion Model Imbalanced Classification
Data Science and AI, Computer Science and Engineering Department, Chalmers University of Technology and University of Gothenburg · International School of Advanced Studies (SISSA), Trieste, Italy · Department of Computing Sciences, Bocconi University, Milano, Italy +2
Expert Routing for Communication-Efficient MoE via Finite Expert Banks
May 6, 2026Mohammad Reza Deylam Salehi, Ali KhalesiMixture-Of-Expert Inference Mixture-Of-Experts
IEEE Graduate Member · Nice, France · Institut Polytechnique des Sciences Avancées (IPSA) +1
Complexity of Linear Regions in Self-supervised Deep ReLU Networks
Apr 27, 2026Mufhumudzi Muthivhi, Terence L. van ZylSelf-Supervised Learning Rectified Linear Unit
University of Johannesburg, Johannesburg, South Africa
Useful nonrobust features are ubiquitous in biomedical images
Apr 24, 2026Coenraad Mouton, Randle Rabe, Niklas C. Koser +4Medical Image Classification Medical Imaging
Section Biomedical Imaging, Department of Radiology and Neuroradiology, University Hospital Schleswig-Holstein, Kiel University · Faculty of Engineering, North-West University, South Africa
Benchmarking PNW Model for MedMNIST to 100% Accuracy
Apr 20, 2026Bo DengMnist Medical Image Classification
Department of Mathematics University of Nebraska-Lincoln Lincoln, NE 68588
Semantic-based Distributed Learning for Diverse and Discriminative Representations
Apr 20, 2026Zhuojun Tian, Chaouki Ben Issaid, Mehdi BennisDecentralized Learning Discriminative Models
Center for Wireless Communications, University of Oulu, Oulu, Finland · Division of Information Science and Engineering, KTH Royal of Technology, Stockholm, Sweden · Center for Wireless Communications, University of Oulu, Oulu 90014, Finland
GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition
Feb 3, 2026Takaya Kawakatsu, Ryo IshiyamaHandwriting Handwritten Text Recognition
Preferred Networks, Inc., Otemachi, Tokyo, Japan · Kyushu University, Fukuoka, Japan
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
Aug 4, 2025Xiaoya Li, Albert Wang, Guoyin Wang +2Approximate Nearest-Neighbor Search Neural Architecture Search
DeepReinforce Team
Inclusive Federated Learning Through Compliance-Weighted Noise Allocation in Healthcare AI
May 28, 2025Santhosh Parampottupadam, Melih Coşğun, Sarthak Pati +7Federated Learning Standard Differential-Privacy
German Cancer Research Center (DKFZ), Division of Medical Image Computing, Heidelberg, Germany · Department of Computer Engineering, Bilkent University, Universiteler 06800 Çankaya/Ankara, Türkiye · Medical Research Group, MLCommons, San Francisco, CA, USA +2
Stochastic Engrams for Efficient Continual Learning
Mar 27, 2025Isabelle Aguilar, Luis Fernando Herbozo Contreras, Omid KaveheiReplay-Based Continual Learning Catastrophic Forgetting
School of Biomedical Engineering, The University of Sydney, NSW, 2006, Australia
Spintronics for image recognition: performance benchmarking via data-driven simulations
Aug 10, 2023Anatole Moureaux, Chloé Chopin, Simon de Wergifosse +2Mnist Magnetic Tunnel Junction
Institute of Condensed Matter and Nanosciences, Université catholique de Louvain, Place Croix du Sud 1, 1348 Louvain-la-Neuve, Belgium · Univ. Grenoble Alpes, CEA, CNRS, Grenoble INP, SPINTEC, 3800 Grenoble, France · Institute for Information and Communication Technologies, Electronics and Applied Mathematics, Université catholique de Louvain, Avenue Georges Lemaître 4, 1348 Louvain-la-Neuve, Belgium
Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
Date pendingRomain Claret, Michael O'Neill, Paul Cotofrei +1Neuroevolution General Grid Search Framework
University of Neuchâtel Neuchâtel, Switzerland · University College Dublin Dublin, Ireland

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

Neural scaling laws and evolution of learnable activation functions of Kolmogorov-Arnold networks

Tilen Cadez, Sanghoon Lee, Kyoung-Min Kim

Asia Pacific Center for Theoretical Physics, Pohang, Gyeongbuk, 37673, Republic of Korea · Department of Physics, Pohang University of Science and Technology, Pohang, Gyeongbuk 37673, Republic of Korea

Kolmogorov-Arnold Networks Scaling Laws Activation Functions Mnist Scaling Evolutionary Optimization Methods

Open paper AskPDF arXiv

Kolmogorov-Arnold Networks (KANs) represent a compelling alternative to traditional Multi-Layer Perceptron (MLP)-based neural networks. By employing activation functions as learnable elements, KANs offer superior interpretability, making them suited for scientific domains. In this work, we investigate the neural scaling laws of KANs and the structural evolution of their learnable activation functions under dataset expansion. Specifically, we evaluate the scaling behavior of three KAN variants---BSRBF-KAN, Gottlieb-KAN, and Faster-KAN---across standard image classification benchmarks (MNIST and Fashion-MNIST) and a specialized scientific regression task (magnetic parameter estimation from domain images of moiré magnetic textures). Our results demonstrate that the test loss

{\cal L}

exhibits a broken neural scaling law (BNSL) behavior as a function of the dataset size

N_D

. After passing through a random-guess regime, the loss follows architecture- and task-dependent scaling behavior. The loss crosses from a faster- to a slower-scaling branch,

{\cal L}\propto N_D^{-α}

and

{\cal L}\propto N_D^{-β}

with

α>β

for image classification tasks. The exponents

α

and

β

depend strongly on both the specific network architecture and the dataset-size regime, ranging from 0.4 to 1.5 and from 0.06 to 0.6, respectively. For the magnetic parameter-regression task, the loss follows a single scaling law with its exponent ranging from 1.28 to 2.59. Additionally, we provide a structural analysis of how activation functions refine their complexity as data volume increases, finding that dataset expansion drives a transition from simple linear-like approximations toward stable, interpretable symbolic forms. These findings provide a quantitative roadmap for the efficient application of KANs while managing the trade-off between model expressivity and computational overhead.

Momentum

Related topics

Latest papers 40