Multilayer Perceptrons

Also known as MLP

Ask about this topic

Overview

Multilayer perceptrons (MLPs) transform inputs through successive layers of weighted connections and nonlinear activations, making them a basic model for classification, regression, and learned feature representations. Research studies how their architecture and training shape approximation, optimization, generalization, robustness, and interpretability, using tools such as gradient-flow analysis, Hessian and kernel methods, and experiments on tasks including tabular prediction and modular arithmetic. Practical work explores gated and residual MLPs, temporal mixers, initialization strategies, and optimizers, often comparing them with convolutional networks, Transformers, tree ensembles, and Kolmogorov–Arnold networks. A central question is when these relatively simple models can match specialized architectures efficiently, and when limitations in data use, stability, or realized expressivity outweigh their simplicity.

Latest papers

CardsList

51 papers6 papers in the last four weeks, up 50% on the four weeks before. 0.0% of all new papers.

  1. Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data

    Nov 2, 2026Rafał Wodziński, Paweł SzczerbiakKolmogorov-Arnold NetworksTabular Classification

    Sano Centre for Computational Medicine, Kraków, Poland · Department of Computer Science, Faculty of Computer Science and Mathematics, Cracow University of Technology, Kraków, Poland · Faculty of Computer Science, AGH University of Krakow, Kraków, Poland

  2. Closed Gates Leak: Decomposing Adjacent-Layer Cancellation in Gated Language Models

    Oct 28, 2026Harvey Dam, Ganesh GopalakrishnanTransformer FFNsMultilayer Perceptrons

    Kahlert School of Computing, University of Utah, Salt Lake City, USA.

  3. Sometimes less is more: Investigating inductive biases of MLPs and Transformers on noisy k-parity features

    Oct 27, 2026Alasdair ParenTransformerMultilayer Perceptrons

    Chalmers University of Technology

  4. Do Neural Models Prefer Their Submodels?

    Oct 20, 2026Alvaro Ribot, Yulia Alexandr, Anna SeigalNeural Network OptimizationMultilayer Perceptrons

    Harvard University · University of Melbourne

  5. Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias

    Oct 15, 2026Yunhao Ni, Yuxin Guo, Jie Luo +2Curse of DimensionalityKolmogorov-Arnold Networks

    State Key Laboratory of Complex and Critical Software Environment, Beihang University, Beijing, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China

  6. Rationally Linearized MLPs

    Oct 9, 2026Arijit Sehanobish, Byeongchan Kim, Avinava Dubey +2Multilayer PerceptronsEfficient Neural Network Inference

    Kensho Technologies · Seoul National University · Google Research +2

  7. Evolutionary Architecture Search for Chlorophyll-aa Prediction in Lakes using Sentinel-2

    Oct 7, 2026Kursat Komurcu, Linas PetkeviciusNeural Architecture SearchRemote Sensing

    Vilnius University, Institute of Computer Science, Artificial Intelligence Methods Lab · IRISA, Universite Bretagne Sud · European Commission Joint Research Center

  8. The Conflict Between Logic and Memory: Training Conditions for Optimizer-Dependent Rule Acquisition

    Sep 30, 2026Gongyue Zhang, Honghai LiuShallow Neural NetworksMultilayer Perceptrons

  9. Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifiers

    Sep 30, 2026Shirin Panahi, Amirhossein Nazerian, Ali PezeshkiDynamical SystemsMultilayer Perceptrons

    Department of Electrical and Computer Engineering Colorado State University Fort Collins, Colorado, USA · Department of Mechanical Engineering Colorado State University Fort Collins, Colorado, USA

  10. Multi-Agent Learning with Cooperation-Driven Optimization Dynamics

    Sep 15, 2026Jarod Ketcha Kouakep, Sreyvi UANN, Timoteo CarlettiMultilayer PerceptronsNeural Network Optimization

    Department of Mathematics and Namur Institute for Complex Systems, naXys, University of Namur, Belgium · Department of Applied Mathematics and Statistics, Institute of Technology of Cambodia, Phnom Penh, Cambodia.

  11. Quantifying the Memorization-to-Generalization Transition: Scaling Laws and Phase Structure in Grokking

    Sep 9, 2026Anish KatariaNeural Network Training DynamicsNeural Scaling Laws

    Princeton University, Princeton, NJ, USA.

  12. Higher Structures in Deep Learning

    Aug 31, 2026Michael L. Roberts, Carlos Zapata Carratalá. Nicholas J. Cooper, Lijun Chen +2Multilayer PerceptronsHypergraph Neural Networks

    Combinatorial Labs · SEMF/Independent Researcher · University of Colorado Boulder

  13. Biologically Inspired Mechanisms for Facilitating Grokking in Multilayer Perceptrons

    Aug 28, 2026Florin LeonGrokkingNeural Network Generalization

    Faculty of Automatic Control and Computer Engineering “Gheorghe Asachi” Technical University of Ias,i Bd. Mangeron 27, 700050 Ias,i, Romania

  14. Linear Independence of Polynomial Compositions and Identifiability of Deep Neural Networks

    Aug 27, 2026Kathlén Kohn, Giovanni Luca Marchetti, Alex Massarenti +1Parameter IdentifiabilityPolynomial Neural Networks

    KTH Stockholm · AI4S AB Stockholm · University of Ferrara

  15. Revenge of Monosemanticity: Neuron Specialization as a New Form of Feature Learning in MLPs

    Aug 25, 2026Amirhesam Abedsoltan, Enric Boix-Adsera, Fivos Kalogiannis +1Multilayer PerceptronsRepresentation Learning

    Department of Computer Science and Engineering, UC San Diego · Department of Statistics and Data Science, The Wharton School, University of Pennsylvania · Halıcıoğlu Data Science Institute, UC San Diego

  16. Width-Independent Compressibility of Deep Neural Networks

    Aug 22, 2026Hong-Yi Wang, Mingze Wang, Liu ZiyinNeural Network CompressionNeural Network Approximation Theory

    Princeton University Princeton, NJ 08544 · Peking University Beijing, China 100871 · Massachusetts Institute of Technology Cambridge, MA 02139

  17. A concentration result for multilayer feedforward neural networks

    Aug 15, 2026Vera KoponenMultilayer PerceptronsFeedforward Neural Networks

  18. A Comparative Analysis of MLP and Kolmogorov-Arnold Networks (KAN) for Faster-than-Nyquist (FTN) Signaling Detection

    Aug 3, 2026Sude Ertan, Osman Tokluoglu, Enver CavusMultilayer PerceptronsKolmogorov-Arnold Networks

    Department of Electrical and Electronics Engineering, Ankara Yıldırım Beyazıt University, Ankara, Turkey

  19. Functional Equivalence and Geometric Diversity in Neural Network Approximations: An Empirical Characterization

    Jul 21, 2026Anuragine S A, Prem JagadeesanMultilayer PerceptronsNeural Representation Geometry

    Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham, Coimbatore, India

  20. Conditioned Direct Feedback Alignment via Activity and Error Geometry

    Jul 20, 2026Houman Safaai, Varun Reddy, Bernardo L. SabatiniMultilayer PerceptronsNeural Network Training Dynamics

    Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University · Department of Neurobiology, Howard Hughes Medical Institute, Harvard Medical School

  21. Building a Neural Network from Scratch: Implementation, Evaluation, and Optimization

    Jul 18, 2026Yuanzhe JiaMultilayer PerceptronsBackpropagation

    University of Sydney, Australia

  22. Is the Statistical Advantage Worth the Cost? An Empirical Comparison of KANs and MLPs for Structured Data Classification

    Jul 15, 2026Matthew Steven P. Toledo, Justine Raphael H. Jacinto, Vivekjeet Singh Chambal +3Multilayer PerceptronsTabular Classification

    Institute of Computer Science, University of the Philippines Los Baños, Philippines · Machine Learning and Artificial Intelligence Applications Lab, University of the Philippines Los Baños, Philippines

  23. Singular perturbations and hierarchical learning in two-layer neural networks

    Jul 12, 2026Cédric Gerbelot, Jean-Christophe MourratMultilayer PerceptronsNeural Network Training Dynamics

    Unité de Mathématiques Pures et Appliquées (UMPA), ENS Lyon · CNRS

  24. A law of robustness for two-layer neural networks with arbitrary weights

    Jul 8, 2026Yitzchak ShmaloNeural Network MemorizationMultilayer Perceptrons

  25. TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning

    Jul 6, 2026Yury Gorishniy, Akim Kotelnikov, Ivan Rubachev +1Multilayer PerceptronsEnsemble Learning

    1Yandex · 2HSE University

  26. From Dataset Spectral Geometry to Network Weights: A Geometry-Aware Initialization for Sigmoidal MLPs in Image Classification

    Jun 26, 2026Yi-Shan ChuMultilayer PerceptronsNeural Network Initialization

    Institute of Statistical Science, Academia Sinica, Taipei, Taiwan (R.O.C.)

  27. Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNs

    Jun 25, 2026Miguel Jaraiz, Fermin Gutierrez, Pablo Yeste +4Multilayer PerceptronsSurrogate Modeling

    ETSIAE-UPM-School of Aeronautics, Universidad Politécnica de Madrid, Plaza Cardenal Cisneros 3, E-28040 Madrid, Spain · Center for Computational Simulation, Universidad Politécnica de Madrid, Campus de Montegancedo, Boadilla del Monte, 28660 Madrid, Spain · Institute for Cross-Disciplinary Physics and Complex Systems (IFISC, CSIC-UIB), 07122 Palma de Mallorca (Spain)

  28. Delta-Position Estimation-Based IMU Odometry: A Comparison of MLP and Kolmogorov-Arnold Networks

    Jun 24, 2026Osman Tokluoglu, Emin KeresteciMultilayer PerceptronsInertial Odometry

    Department of Electrical and Electronics Engineering, Ankara Yıldırım Beyazıt University, Ankara, Türkiye · Department of Computer Engineering, TOBB University of Economics and Technology, Ankara, Türkiye

  29. Gated MLPs as Symmetry-Broken Rank-1 Bilinear Attention

    Jun 20, 2026Nathan BreslowMultilayer PerceptronsSymmetry Breaking

  30. Expressivity Saturation: Reduced Affine Region Usage Under Increasing Task Complexity

    Jun 19, 2026Xuan Qi, Yi Wei, Fanqi Yu +1Multilayer PerceptronsNeural Network Approximation Theory

    AI for Good (AIGO), Istituto Italiano di Tecnologia · DITEN, University of Genoa · State Key Laboratory of Novel Software Technology +1