Tootfinder

Identification of Strongly Lensed Gravitational Wave Events Using Squeeze-and-Excitation Multilayer Perceptron Data-efficient Image Transformer
Dejiang Li, Tonghua Liu, Ao Liu, Cuihong Wen, Jieci Wang, Kai Liao, Jiaxing Cui
https://arxiv.org/abs/2508.19311

Identification of Strongly Lensed Gravitational Wave Events Using Squeeze-and-Excitation Multilayer Perceptron Data-efficient Image Transformer
With the advancement of third-generation gravitational wave detectors, the identification of strongly lensed gravitational wave (GW) events is expected to play an increasingly vital role in cosmology and fundamental physics. However, traditional Bayesian inference methods suffer from combinatorial computational overhead as the number of events grows, making real-time analysis infeasible. To address this, we propose a deep learning model named Squeeze-and-Excitation Multilayer Perceptron Data-ef…

Algebraic Approach to Ridge-Regularized Mean Squared Error Minimization in Minimal ReLU Neural Network
Ryoya Fukasaku, Yutaro Kabata, Akifumi Okuno
https://arxiv.org/abs/2508.17783

Algebraic Approach to Ridge-Regularized Mean Squared Error Minimization in Minimal ReLU Neural Network
This paper investigates a perceptron, a simple neural network model, with ReLU activation and a ridge-regularized mean squared error (RR-MSE). Our approach leverages the fact that the RR-MSE for ReLU perceptron is piecewise polynomial, enabling a systematic analysis using tools from computational algebra. In particular, we develop a Divide-Enumerate-Merge strategy that exhaustively enumerates all local minima of the RR-MSE. By virtue of the algebraic formulation, our approach can identify not o…

Machine Learning based Radio Environment Map Estimation for Indoor Visible Light Communication
Helena Serpi (Tanya), Christina (Tanya), Politi
https://arxiv.org/abs/2507.19149

Machine Learning based Radio Environment Map Estimation for Indoor Visible Light Communication
An innovative method for radio map estimation in optical wireless communications is proposed that is based on Machine Learning rather than simulation techniques. Multi-Layer Perceptron (MLP) representation of indoor Visible Light Communication (VLC) systems is suggested, and signal propagation is estimated. The simulation and performance predictions are accurate, fast and require a reduced set of training sample size with respect to other counterparts, making this solution very suitable for rea…

Comment on "Storage properties of a quantum perceptron"
Mauro Pastore
https://arxiv.org/abs/2506.18431 https://arxiv.org/pd…

Comment on "Storage properties of a quantum perceptron"
The recent paper "Storage properties of a quantum perceptron" [Phys. Rev. E 110, 024127] considers a quadratic constraint satisfaction problem, motivated by a quantum version of the perceptron. In particular, it derives its critical capacity, the density of constraints at which there is a satisfiability transition. The same problem was considered before in another context (classification of geometrically structured inputs, see [Phys. Rev. Lett. 125, 120601; Phys. Rev. E 102, 032119; J. Stat. Me…

Robust Anomaly Detection in Network Traffic: Evaluating Machine Learning Models on CICIDS2017
Zhaoyang Xu, Yunbo Liu
https://arxiv.org/abs/2506.19877 https…

Robust Anomaly Detection in Network Traffic: Evaluating Machine Learning Models on CICIDS2017
Identifying suitable machine learning paradigms for intrusion detection remains critical for building effective and generalizable security solutions. In this study, we present a controlled comparison of four representative models - Multi-Layer Perceptron (MLP), 1D Convolutional Neural Network (CNN), One-Class Support Vector Machine (OCSVM) and Local Outlier Factor (LOF) - on the CICIDS2017 dataset under two scenarios: detecting known attack types and generalizing to previously unseen threats. O…

Enhanced Image Recognition Using Gaussian Boson Sampling
Si-Qiu Gong, Ming-Cheng Chen, Hua-Liang Liu, Hao Su, Yi-Chao Gu, Hao-Yang Tang, Meng-Hao Jia, Yu-Hao Deng, Qian Wei, Hui Wang, Han-Sen Zhong, Xiao Jiang, Li Li, Nai-Le Liu, Chao-Yang Lu, Jian-Wei Pan
https://arxiv.org/abs/2506.19707

Enhanced Image Recognition Using Gaussian Boson Sampling
Gaussian boson sampling (GBS) has emerged as a promising quantum computing paradigm, demonstrating its potential in various applications. However, most existing works focus on theoretical aspects or simple tasks, with limited exploration of its capabilities in solving real-world practical problems. In this work, we propose a novel GBS-based image recognition scheme inspired by extreme learning machine (ELM) to enhance the performance of perceptron and implement it using our latest GBS device, J…

Control of pedestal-top electron density using RMP and gas puff at KSTAR
Minseok Kim, S. K. Kim, A. Rothstein, P. Steiner, K. Erickson, Y. H. Lee, H. Han, Sang-hee Hahn, J. W. Juhn, B. Kim, R. Shousha, C. S. Byun, J. Butt, ChangMin Shin, J. Hwang, Minsoo Cha, Hiro Farre, S. M. Yang, Q. Hu, D. Eldon, N. C. Logan, A. Jalalvand, E. Kolemen
https://

Control of pedestal-top electron density using RMP and gas puff at KSTAR
We report the experimental results of controlling the pedestal-top electron density by applying resonant magnetic perturbation with the in-vessel control coils and the main gas puff in the 2024-2025 KSTAR experimental campaign. The density is reconstructed using a parametrized psi_N grid and the five channels of the line-averaged density measured by a two-colored interferometer. The reconstruction procedure is accelerated by deploying a multi-layer perceptron to run in about 120 microseconds an…

Advanced For-Loop for QML algorithm search
FuTe Wong
https://arxiv.org/abs/2506.18260 https://arxiv.org/pdf/2506.18260

Advanced For-Loop for QML algorithm search
This paper introduces an advanced framework leveraging Large Language Model-based Multi-Agent Systems (LLMMA) for the automated search and optimization of Quantum Machine Learning (QML) algorithms. Inspired by Google DeepMind's FunSearch, the proposed system works on abstract level to iteratively generates and refines quantum transformations of classical machine learning algorithms (concepts), such as the Multi-Layer Perceptron, forward-forward and backpropagation algorithms. As a proof of conc…

Rare dense solutions clusters in asymmetric binary perceptrons -- local entropy via fully lifted RDT
Mihailo Stojnic
https://arxiv.org/abs/2506.19276 https…

Rare dense solutions clusters in asymmetric binary perceptrons -- local entropy via fully lifted RDT
We study classical asymmetric binary perceptron (ABP) and associated \emph{local entropy} (LE) as potential source of its algorithmic hardness. Isolation of \emph{typical} ABP solutions in SAT phase seemingly suggests a universal algorithmic hardness. Paradoxically, efficient algorithms do exist even for constraint densities $α$ fairly close but at a finite distance (\emph{computational gap}) from the capacity. In recent years, existence of rare large dense clusters and magical ability of fast…

I have decided to suffer, and hence made a genetic algorithm that through linear algebra generates colours palettes to be automatically scored by a small perceptron that will be live trained by a human who will pick a score for a sample of palettes, all to try and generate automatically colour palettes that an artist could find appealing for the sole goal to figure out if colour pleasantness is evaluable and/or reproducible by linear algebra
It is 1:30 AM and I have a full backend, 4 t…

GratNet: A Photorealistic Neural Shader for Diffractive Surfaces
Narayan Kandel, Daljit Singh J. S. Dhillon
https://arxiv.org/abs/2506.15815 https://

GratNet: A Photorealistic Neural Shader for Diffractive Surfaces
Structural coloration is commonly modeled using wave optics for reliable and photorealistic rendering of natural, quasi-periodic and complex nanostructures. Such models often rely on dense, preliminary or preprocessed data to accurately capture the nuanced variations in diffractive surface reflectances. This heavy data dependency warrants implicit neural representation which has not been addressed comprehensively in the current literature. In this paper, we present a multi-layer perceptron (MLP…

Brain Stroke Classification Using Wavelet Transform and MLP Neural Networks on DWI MRI Images
Mana Mohammadi, Amirhesam Jafari Rad, Ashkan Behrouzi
https://arxiv.org/abs/2506.15364

Brain Stroke Classification Using Wavelet Transform and MLP Neural Networks on DWI MRI Images
This paper presents a lightweight framework for classifying brain stroke types from Diffusion-Weighted Imaging (DWI) MRI scans, employing a Multi-Layer Perceptron (MLP) neural network with Wavelet Transform for feature extraction. Accurate and timely stroke detection is critical for effective treatment and improved patient outcomes in neuroimaging. While Convolutional Neural Networks (CNNs) are widely used for medical image analysis, their computational complexity often hinders deployment in re…

Learning Internal Biological Neuron Parameters and Complexity-Based Encoding for Improved Spiking Neural Networks Performance
Zofia Rudnicka, Janusz Szczepanski, Agnieszka Pregowska
https://arxiv.org/abs/2508.11674

Learning Internal Biological Neuron Parameters and Complexity-Based Encoding for Improved Spiking Neural Networks Performance
This study introduces a novel approach by replacing the traditional perceptron neuron model with a biologically inspired probabilistic meta neuron, where the internal neuron parameters are jointly learned, leading to improved classification accuracy of spiking neural networks (SNNs). To validate this innovation, we implement and compare two SNN architectures: one based on standard leaky integrate-and-fire (LIF) neurons and another utilizing the proposed probabilistic meta neuron model. As a sec…

Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models
Tuan Dat Phuong, Long-Vu Hoang, Huy Dat Tran
https://arxiv.org/abs/2506.14153

Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models
Recent advancements in speech synthesis technologies have led to increasingly advanced spoofing attacks, posing significant challenges for automatic speaker verification systems. While systems based on self-supervised learning (SSL) models, particularly the XLSR-Conformer model, have demonstrated remarkable performance in synthetic speech detection, there remains room for architectural improvements. In this paper, we propose a novel approach that replaces the traditional Multi-Layer Perceptron …

Machine Learning-Based Estimation of Monthly GDP
Yonggeun Jung
https://arxiv.org/abs/2506.14078 https://arxiv.org/pdf/2506.14078

Machine Learning-Based Estimation of Monthly GDP
This paper proposes a scalable framework to estimate monthly GDP using machine learning methods. We apply Multi-Layer Perceptron (MLP), Long Short-Term Memory networks (LSTM), Extreme Gradient Boosting (XGBoost), and Elastic Net regression to map monthly indicators to quarterly GDP growth, and reconcile the outputs with actual aggregates. Using data from China, Germany, the UK, and the US, our method delivers robust performance across varied data environments. Benchmark comparisons with prior U…

Jigsaw: Training Multi-Billion-Parameter AI Weather Models with Optimized Model Parallelism
Deifilia Kieckhefen, Markus G\"otz, Lars H. Heyen, Achim Streit, Charlotte Debus
https://arxiv.org/abs/2507.05753

Jigsaw: Training Multi-Billion-Parameter AI Weather Models with Optimized Model Parallelism
AI-based methods have revolutionized atmospheric forecasting, with recent successes in medium-range forecasting spurring the development of climate foundation models. Accurate modeling of complex atmospheric dynamics at high spatial resolutions and longer lead times requires large neural networks and gigabyte-sized data samples, making accelerator memory and I/O-bandwidth the bottlenecks for model training. We introduce WeatherMixer, a multi-layer-perceptron-based architecture whose workload sc…

HAWC Performance Enhanced by Machine Learning in Gamma-Hadron Separation
R. Alfaro, C. Alvarez, A. Andr\'es, E. Anita-Rangel, M. Araya, J. C. Arteaga-Vel\'azquez, D. Avila Rojas, H. A. Ayala Solares, R. Babu, P. Bangale, E. Belmont-Moreno, A. Bernal, T. Capistr\'an, A. Carrami\~nana, F. Carre\'on, S. Casanova, U. Cotti, E. De la Fuente, D. Depaoli, P. Desiati, N. Di Lalla, R. Diaz Hernandez, M. A. DuVernois, J. C. D\'iaz-V\'elez, K. Engel, T. Ergin, C. Espinoza,…

HAWC Performance Enhanced by Machine Learning in Gamma-Hadron Separation
Improving gamma-hadron separation is one of the most effective ways to enhance the performance of ground-based gamma-ray observatories. With over a decade of continuous operation, the High-Altitude Water Cherenkov (HAWC) Observatory has contributed significantly to high-energy astrophysics. To further leverage its rich dataset, we introduce a machine learning approach for gamma-hadron separation. A Multilayer Perceptron shows the best performance, surpassing traditional and other Machine Learni…

The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness
Gnankan Landry Regis N'guessan, Issa Karambal
https://arxiv.org/abs/2506.13825

The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness
Research on artificial consciousness lacks the equivalent of the perceptron: a small, trainable module that can be copied, benchmarked, and iteratively improved. We introduce the Reflexive Integrated Information Unit (RIIU), a recurrent cell that augments its hidden state $h$ with two additional vectors: (i) a meta-state $μ$ that records the cell's own causal footprint, and (ii) a broadcast buffer $B$ that exposes that footprint to the rest of the network. A sliding-window covariance and a dif…

Evaluation of Machine Learning Models in Student Academic Performance Prediction
A. G. R. Sandeepa, Sanka Mohottala
https://arxiv.org/abs/2506.08047 https:…

Evaluation of Machine Learning Models in Student Academic Performance Prediction
This research investigates the use of machine learning methods to forecast students' academic performance in a school setting. Students' data with behavioral, academic, and demographic details were used in implementations with standard classical machine learning models including multi-layer perceptron classifier (MLPC). MLPC obtained 86.46% maximum accuracy for test set across all implementations. Under 10-fold cross validation, MLPC obtained 79.58% average accuracy for test set while for train…

Discrimination of neutron-$\gamma$ in the low energy regime using machine learning for an EJ-276D plastic scintillator
S. Panda (a,b), P. K. Netrakanti (a), S. P. Behera (a,b), R. R. Sahu (a), K. Kumar (a,b), R. Sehgal (a), D. K. Mishra (a,b), V. Jha (a,b)
https://arxiv.org/abs/2506.13802

Discrimination of neutron-$γ$ in the low energy regime using machine learning for an EJ-276D plastic scintillator
In this work, we present results for discrimination of neutron and $γ$ events using a plastic scintillator detector with pulse shape discrimination capabilities. Machine learning (ML) algorithms are used to improve the discriminatory power between neutron and $γ$ events at lower energy ranges which otherwise are not addressed by the conventional pulse shape discrimination techniques. The use of a multilayer perceptron with Bayesian inference (MLPBNN) and support vector machine (SVM) algorithm…

EVA-S2PMLP: Secure and Scalable Two-Party MLP via Spatial Transformation
Shizhao Peng, Shoumo Li, Tianle Tao
https://arxiv.org/abs/2506.15102 https://

EVA-S2PMLP: Secure and Scalable Two-Party MLP via Spatial Transformation
Privacy-preserving neural network training in vertically partitioned scenarios is vital for secure collaborative modeling across institutions. This paper presents \textbf{EVA-S2PMLP}, an Efficient, Verifiable, and Accurate Secure Two-Party Multi-Layer Perceptron framework that introduces spatial-scale optimization for enhanced privacy and performance. To enable reliable computation under real-number domain, EVA-S2PMLP proposes a secure transformation pipeline that maps scalar inputs to vector a…

Estimation of Electron Screening Potential in the 6Li(d,{\alpha})4He Reaction Using Multi-Layer Perceptron Neural Network
D. Chattopadhyay
https://arxiv.org/abs/2506.08044

Estimation of Electron Screening Potential in the 6Li(d,α)4He Reaction Using Multi-Layer Perceptron Neural Network
Reactions between light charged nuclei at sub-Coulomb energies are crucial in astrophysical environments, but accurate cross-section measurements are hindered by electron screening. Traditional methods, including polynomial extrapolation and the Trojan Horse Method, often yield screening potentials exceeding adiabatic predictions. Building on the success of an MLP-based Artificial Neural Network (ANN) for the 6Li(p, α)3He reaction [1], this work applies the same approach to the 6Li(d, α)4He r…

Feasibility Study of CNNs and MLPs for Radiation Heat Transfer in 2-D Furnaces with Spectrally Participative Gases
Axel TahmasebiMoradi, Vincent Ren, Benjamin Le-Creurer, Chetra Mang
https://arxiv.org/abs/2506.08033

Feasibility Study of CNNs and MLPs for Radiation Heat Transfer in 2-D Furnaces with Spectrally Participative Gases
Aiming to reduce the computational cost of numerical simulations, a convolutional neural network (CNN) and a multi-layer perceptron (MLP) are introduced to build a surrogate model to approximate radiative heat transfer solutions in a 2-D walled domain with participative gases. The originality of this work lays in the adaptation of the inputs of the problem (gas and wall properties) in order to fit with the CNN architecture, more commonly used for image processing. Two precision datasets have be…

Network-Specific Models for Multimodal Brain Response Prediction
Andrea Corsico, Giorgia Rigamonti, Simone Zini, Luigi Celona, Paolo Napoletano
https://arxiv.org/abs/2508.06499 …

Network-Specific Models for Multimodal Brain Response Prediction
In this work, we present a network-specific approach for predicting brain responses to complex multimodal movies, leveraging the Yeo 7-network parcellation of the Schaefer atlas. Rather than treating the brain as a homogeneous system, we grouped the seven functional networks into four clusters and trained separate multi-subject, multi-layer perceptron (MLP) models for each. This architecture supports cluster-specific optimization and adaptive memory modeling, allowing each model to adjust tempo…

Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings
Binbin Xu, G\'erard Dray
https://arxiv.org/abs/2507.03122 h…

Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings
This study investigates the feasibility and performance of federated learning (FL) for multi-label ICD code classification using clinical notes from the MIMIC-IV dataset. Unlike previous approaches that rely on centralized training or fine-tuned large language models, we propose a lightweight and scalable pipeline combining frozen text embeddings with simple multilayer perceptron (MLP) classifiers. This design offers a privacy-preserving and deployment-efficient alternative for clinical NLP app…

Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems
Haoran Sun, Daoqi Liu, Hongyu Zhou, Maokun Li, Shenheng Xu, Fan Yang
https://arxiv.org/abs/2508.10555

Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems
Inverse scattering problems are critical in electromagnetic imaging and medical diagnostics but are challenged by their nonlinearity and diverse measurement scenarios. This paper proposes a physics-informed deep contrast source inversion framework (DeepCSI) for fast and accurate medium reconstruction across various measurement conditions. Inspired by contrast source inversion (CSI) and neural operator methods, a residual multilayer perceptron (ResMLP) is employed to model current distributions …

PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism
Yuyan Ye, Hang Xu, Yanghang Huang, Jiali Huang, Qian Weng
https://arxiv.org/abs/2508.13228

PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism
This paper proposes PreSem-Surf, an optimized method based on the Neural Radiance Field (NeRF) framework, capable of reconstructing high-quality scene surfaces from RGB-D sequences in a short time. The method integrates RGB, depth, and semantic information to improve reconstruction performance. Specifically, a novel SG-MLP sampling structure combined with PR-MLP (Preconditioning Multilayer Perceptron) is introduced for voxel pre-rendering, allowing the model to capture scene-related information…

This https://arxiv.org/abs/2505.02580 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Temperature and pressure reconstruction in turbulent Rayleigh-Bénard convection by Lagrangian velocities using PINN
Velocity, pressure, and temperature are the key variables for understanding thermal convection, and measuring them all is a complex task. In this paper, we demonstrate a method to reconstruct temperature and pressure fields based on given Lagrangian velocity data. A physics-informed neural network (PINN) based on a multilayer perceptron architecture and a periodic sine activation function is used to reconstruct both the temperature and the pressure for two cases of turbulent Rayleigh-Bénard co…

Classification by Separating Hypersurfaces: An Entropic Approach
Argimiro Arratia, Mahmoud El Daou, Henryk Gzyl
https://arxiv.org/abs/2507.02732 https://…

Classification by Separating Hypersurfaces: An Entropic Approach
We consider the following classification problem: Given a population of individuals characterized by a set of attributes represented as a vector in ${\mathbb R}^N$, the goal is to find a hyperplane in ${\mathbb R}^N$ that separates two sets of points corresponding to two distinct classes. This problem, with a history dating back to the perceptron model, remains central to machine learning. In this paper we propose a novel approach by searching for a vector of parameters in a bounded $N$-dimensi…

Overlap Gap and Computational Thresholds in the Square Wave Perceptron
Marco Benedetti, Andrej Bogdanov, Enrico M. Malatesta, Marc M\'ezard, Gianmarco Perrupato, Alon Rosen, Nikolaj I. Schwartzbach, Riccardo Zecchina
https://arxiv.org/abs/2506.05197

Overlap Gap and Computational Thresholds in the Square Wave Perceptron
Square Wave Perceptrons (SWPs) form a class of neural network models with oscillating activation function that exhibit intriguing ``hardness'' properties in the high-dimensional limit at a fixed signal-to-noise ratio $α= O(1)$. In this work, we examine two key aspects of these models. The first is related to the so-called overlap-gap property, that is a disconnectivity feature of the geometry of the solution space of combinatorial optimization problems proven to cause the failure of a large fa…

This https://arxiv.org/abs/2506.05588 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC systems benefit from their dynamic properties, which make them ideal for reservoir construction. However, achieving high performance in memristor-based RC remains challenging, as it critically depends on the input preprocessing method and reservoir size. Despite …

First Experience with Real-Time Control Using Simulated VQC-Based Quantum Policies
Yize Sun, Mohamad Hagog, Marc Weber, Daniel Hein, Steffen Udluft, Volker Tresp, Yunpu Ma
https://arxiv.org/abs/2508.01690

First Experience with Real-Time Control Using Simulated VQC-Based Quantum Policies
This paper investigates the integration of quantum computing into offline reinforcement learning and the deployment of the resulting quantum policy in a real-time control hardware realization of the cart-pole system. Variational Quantum Circuits (VQCs) are used to represent the policy. Classical model-based offline policy search was applied, in which a pure VQC with trainable input-output weights is used as a policy network instead of a classical multilayer perceptron. The goal is to evaluate t…

This https://arxiv.org/abs/2505.12494 has been replaced.
initial toot: https://mastoxiv.page/@arX…

SMURF: Scalable method for unsupervised reconstruction of flow in 4D flow MRI
We introduce SMURF, a scalable and unsupervised machine learning method for simultaneously segmenting vascular geometries and reconstructing velocity fields from 4D flow MRI data. SMURF models geometry and velocity fields using multilayer perceptron-based functions incorporating Fourier feature embeddings and random weight factorization to accelerate convergence. A measurement model connects these fields to the observed image magnitude and phase data. Maximum likelihood estimation and subsampli…

Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks
Sergei Gleyzer, Hanh Nguyen, Dinesh P. Ramakrishnan, Eric A. F. Reinhardt
https://arxiv.org/abs/2508.00247 https:…

Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks
The Kolmogorov-Arnold representation theorem states that any continuous multivariable function can be exactly represented as a finite superposition of continuous single variable functions. Subsequent simplifications of this representation involve expressing these functions as parameterized sums of a smaller number of unique monotonic functions. These developments led to the proof of the universal approximation capabilities of multilayer perceptron networks with sigmoidal activations, forming th…

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Rishona Daniels, Duna Wattad, Ronny Ronen, David Saad, Shahar Kvatinsky
https://arxiv.org/abs/2506.05588

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC systems benefit from their dynamic properties, which make them ideal for reservoir construction. However, achieving high performance in memristor-based RC remains challenging, as it critically depends on the input preprocessing method and reservoir size. Despite …

Neural Visibility Cache for Real-Time Light Sampling
Jakub Bok\v{s}ansk\'y, Daniel Meister
https://arxiv.org/abs/2506.05930 https://

Neural Visibility Cache for Real-Time Light Sampling
Direct illumination with many lights is an inherent component of physically-based rendering, remaining challenging, especially in real-time scenarios. We propose an online-trained neural cache that stores visibility between lights and 3D positions. We feed light visibility to weighted reservoir sampling (WRS) to sample a light source. The cache is implemented as a fully-fused multilayer perceptron (MLP) with multi-resolution hash-grid encoding, enabling online training and efficient inference o…

This https://arxiv.org/abs/2506.05197 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Overlap Gap and Computational Thresholds in the Square Wave Perceptron
Square Wave Perceptrons (SWPs) form a class of neural network models with oscillating activation function that exhibit intriguing ``hardness'' properties in the high-dimensional limit at a fixed signal-to-noise ratio $α= O(1)$. In this work, we examine two key aspects of these models. The first is related to the so-called overlap-gap property, that is a disconnectivity feature of the geometry of the solution space of combinatorial optimization problems proven to cause the failure of a large fa…

Liquid and solid layers in a thermal deep learning machine
Gang Huang, Lai Shun Chan, Hajime Yoshino, Ge Zhang, Yuliang Jin
https://arxiv.org/abs/2506.06789

Liquid and solid layers in a thermal deep learning machine
Based on deep neural networks (DNNs), deep learning has been successfully applied to many problems, but its mechanism is still not well understood -- especially the reason why over-parametrized DNNs can generalize. A recent statistical mechanics theory on supervised learning by a prototypical multi-layer perceptron (MLP) on some artificial learning scenarios predicts that adjustable parameters of over-parametrized MLPs become strongly constrained by the training data close to the input/output b…