Machine Learning and ELM

Últimos artículos

• Machine Unlearning for Gibbs Supervised Learning Algorithms

  Yaiza Bermudez, Samir M. Perlaza, I\~naki Esnaola · 25 de septiembre de 2026

  In this paper, a method for achieving exact unlearning for Gibbs supervised learning algorithms is proposed using a variational formulation inspired by empirical risk minimization subject to relative entropy regularization (ERM-RER). Such a method consists of maximizing the expected empirical risk o…

• An Analytical Theory of Auxiliary Learning

  Federico Milanesio, Alessandro Ingrosso, Matteo Osella · 25 de septiembre de 2026

  Auxiliary learning is an optimization paradigm in which a neural network's performance on a target task is improved by jointly training it on additional tasks. However, the mechanisms behind this improvement remain poorly understood. We study this problem using a teacher-student framework and derive…

• RoBell-RVFL: A Robust Generalized Bell Random Vector Functional Link Network

  A. Rahaman, A. Quadir, M. Tanveer · 18 de agosto de 2026

  The dominance of majority classes in real-world datasets poses a fundamental challenge to randomized neural networks, often biasing decision boundaries and overlooking critical minority samples. Existing remedies, such as synthetic minority over-sampling (SMOTE) and class-weighted loss functions, pr…

• Fisher Information based Stochastic Gradient Ascent for Online Learning of Dirichlet Process Mixture and Theory

  Kart-Leong Lim, Xudong Jiang · 28 de julio de 2026

  Scalable algorithms of posterior approximation allow Bayesian nonparametrics such as Dirichlet process mixture to scale up to larger dataset at fractional cost. Recent algorithms, notably the stochastic variational inference performs local learning from minibatch. The main problem with stochastic va…

• A Statistical Difference between Single-Layer Learning and Hierarchical Learning in Wide Neural Networks

  Sumio Watanabe · 28 de julio de 2026

  Hierarchical neural networks are widely used in artificial intelligence, yet their mathematical properties remain incompletely understood. In the infinite-width limit, two different theoretical frameworks have been proposed. One reduces deep learning to kernel regression with a fixed kernel by assum…

• XGRVFL-MV: Residual-Coupled Graph-Embedded Multi-View Random Vector Functional Link Network with FleXi Guardian Loss

  Yogesh Kumar, Mudasir Ganaie · 28 de julio de 2026

  Random Vector Functional Link (RVFL) networks provide an efficient randomized learning framework for classification. Existing multi-view RVFL methods utilize complementary information from multiple views. However, preserving view-specific geometric structure, limiting the influence of large predicti…

• Differentially Private Neural Network Training Under the Hidden State Assumption

  Ding Chen, Haochen Luo, Xiaofei Wang, Chen Liu · 23 de julio de 2026

  Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over training steps, while aggregation-based approaches such as PATE suffer from data inefficiency due to disjoint data partitioning. We propose \textbf{Differen…

• Graph-Embedded Intuitionistic Fuzzy Broad Learning System: A Multi-view Framework

  Yogesh Kumar, Manju, Mudasir Ganaie · 21 de julio de 2026

  The Broad Learning System (BLS) has been widely used for data classification and is based on a layer-by-layer feed-forward structure. However, it gives the same importance to all data points, which reduces its effectiveness on real-world datasets with noise and outliers. In addition, it does not con…

• Spectral Stability of Pseudoinverse-Based Extreme Learning Machine

  Bich Van Nguyen, Ngoc Anh Khong · 10 de julio de 2026

  Extreme Learning Machine (ELM) computes output weights analytically using the Moore-Penrose pseudoinverse. Although this leads to fast training, its numerical stability depends strongly on the conditioning of the hidden layer matrix. This paper studies pseudoinverse-based ELM from a spectral perspec…

• Deep Learning Method for Stationary Distribution of Reflected Brownian Motion

  Jim Dai, Zhanhao Zhang · 10 de julio de 2026

  The stationary distribution of reflected Brownian motion (RBM) plays an important role in the analysis of high-dimensional stochastic systems, yet closed-form solutions are known only for a few special cases. Computing important performance metrics, such as tail probabilities, is even more intractab…

• On the Principles of Deep Feedforward ReLU Networks

  Changcun Huang · 9 de julio de 2026

  The architecture of deep feedforward neural networks is ubiquitous in deep learning, either as a whole system or as a subnetwork of other architectures, and thus its mechanism is a key ingredient of the black box of neural networks. On the basis of the simplest two-layer ReLU network, this paper sys…

• Frequency Shift Physics-Informed Extreme Learning Machine for Solving High-Frequency Partial Differential Equations

  Xiong Xiong, Ruonan Zhai, Zheng Zeng, Sheng Zhou, Rongchun Hu, Zichen Deng · 3 de julio de 2026

  Solving partial differential equations (PDEs) with high-frequency solutions remains a central challenge in physics-informed machine learning due to spectral bias -- the tendency of neural networks to learn low-frequency components preferentially. This paper proposes a Frequency Shift Physics-Informe…

• Fractional Stochastic Neural Networks

  Yuecai Han, Jianming Xu · 30 de junio de 2026

  In this paper, we develop a fractional stochastic neural network with residual dynamics driven by fractional Brownian motion. By introducing a discrete stochastic maximum principle for the network, we construct the corresponding adjoint recursion. For deterministic network parameters, we prove mean …

• Sequential Minimal Optimization Algorithm for One-Class Support Vector Machines With Privileged Information

  Andrey Lange, Dmitry Smolyakov, Evgeny Burnaev · 23 de junio de 2026

  One of the powerful techniques in data modeling is accounting for features that are available at the training stage, but are not available when the trained model is used to classify or predict test data -- the Learning Using Privileged Information paradigm (LUPI). Sequential Minimal Optimization (SM…

• Towards Critical Branching Mechanism in Recurrent Neural Networks

  Feixiang Ren, Ling Feng · 10 de junio de 2026

  Criticality has been proposed as a key organizing principle in biological neural systems, yet its origin and relevance in artificial neural networks remain unclear. We analyze hidden-state dynamics in trained long short-term memory (LSTM) networks and show that small networks near their optimal trai…

• A Robust $\widetilde{\mathcal{O}}(1/\sqrt{T})$ Rate for Unprojected TD Learning with Linear Function Approximation

  Wei-Cheng Lee, Francesco Orabona · 9 de junio de 2026

  We investigate the finite-time convergence properties of Temporal Difference (TD) learning with linear function approximation, a cornerstone of reinforcement learning. We are interested in the so-called ``robust'' setting, where the convergence guarantee does not depend on the potential function's…

• HalfNet: Randomized Neural Networks with Learned Subspace Geometry

  Ethem Alpaydin · 4 de junio de 2026

  Many researchers investigated neural networks with some of their weights fixed to values randomly drawn from a given distribution, e.g., $N(0, I)$. Our proposed HalfNet draws random weights from $N(0, \Sigma)$, where $\Sigma$, which defines the geometry of the distribution, has a low-rank factorizat…

• Evolutionary Extreme Learning Machine of ab-initio Energy Landscapes for Crystal Structure Prediction using Manta Ray Optimization with Levy Flight

  Adrian Rubio-Solis · 19 de mayo de 2026

  The Manta Ray Foraging Optimization algorithm (MRFO) has proven to be a powerful heuristic strategy in the optimal solution of a large number of engineering problems. In this paper, an improvement of MRFO with Levy Flight is suggested for the training of extreme learning machines (ELMs) whose basic …

• CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks

  Mushir Akhtar, M. Tanveer, Mohd. Arshad · 14 de mayo de 2026

  Randomized neural networks (RdNNs) enable efficient, backpropagation-free training by freezing randomly initialized input-to-hidden weights, which permits a closed-form solution for the output layer. However, conventional random initialization is blind to inter-feature dependence, ignoring correlati…

• Nonparametric Sparse Online Learning of the Koopman Operator

  Boya Hou, Sina Sanjari, Nathan Dahlin, Alec Koppel, Subhonmesh Bose · 16 de abril de 2026

  The Koopman operator provides a powerful framework for representing the dynamics of general nonlinear dynamical systems. However, existing data-driven approaches to learning the Koopman operator rely on batch data. In this work, we present a sparse online learning algorithm that learns the Koopman o…

• Universal Approximation with XL MIMO Systems: OTA Classification via Trainable Analog Combining

  Kyriakos Stylianopoulos, George C. Alexandropoulos · 13 de abril de 2026

  In this paper, we show that an eXtremely Large (XL) Multiple-Input Multiple-Output (MIMO) wireless system with appropriate analog combining components exhibits the properties of a universal function approximator, similar to a feedforward neural network. By treating the channel coefficients as the ra…

• Integer-Only Operations on Extreme Learning Machine Test Time Classification

  Emerson Lopes Machadoa, Cristiano Jacques Miosso, Ricardo Pezzuol Jacobi · 7 de abril de 2026

  We present a theoretical analysis and empirical evaluations of a novel set of techniques for computational cost reduction of test time operations of network classifiers based on extreme learning machine (ELM). By exploring some characteristics we derived from these models, we show that the classific…

• Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ

  Han-Dong Lim, HyeAnn Lee, Donghwan Lee · 31 de marzo de 2026

  Reinforcement learning has witnessed significant advancements, particularly with the emergence of model-based approaches. Among these, $Q$-learning has proven to be a powerful algorithm in model-free settings. However, the extension of $Q$-learning to a model-based framework remains relatively unexp…

• FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation

  Dong Liu, Yanxuan Yu, Jiayi Zhang, Yifan Li, Ben Lengerich, Ying Nian Wu · 30 de marzo de 2026

  Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks. To alleviate this inefficiency, we propose \textbf{FastCache}, a hidden-state-level caching and compression framework that accelerates DiT …

• Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features

  Jiuqi Wang, Shangtong Zhang · 25 de marzo de 2026

  Temporal difference (TD) learning with linear function approximation (linear TD) is a classic and powerful prediction algorithm in reinforcement learning. While it is well-understood that linear TD converges almost surely to a unique point, this convergence traditionally requires the assumption that…