Tootfinder

{\L}ukasiewicz Logic with Actions for Neural Networks training
Ioana Leu\c{s}tean (University of Bucharest), Bogdan Macovei (University of Bucharest)
https://arxiv.org/abs/2509.13020

Łukasiewicz Logic with Actions for Neural Networks training
Based on the already known connection between multilayer perceptrons and Lukasiewicz logic with rational coefficients, we take a step forward in analyzing its training process using a three-sorted hybrid modal logic: a multilayer perceptron is a logical formula; the actions of the training process are modal operators; the training process is a sequence of logical deductions. Using the proof assistant and the programming language Lean 4, the algorithmic implementation of the training process is …

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
Arthur Bizzi, Matias Grynberg, Vitor Matias, Daniel Perazzo, Jo\~ao Paulo Lima, Luiz Velho, Nuno Gon\c{c}alves, Jo\~ao Pereira, Guilherme Schardong, Tiago Novello
https://arxiv.org/abs/2510.09537

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
Morphing is a long-standing problem in vision and computer graphics, requiring a time-dependent warping for feature alignment and a blending for smooth interpolation. Recently, multilayer perceptrons (MLPs) have been explored as implicit neural representations (INRs) for modeling such deformations, due to their meshlessness and differentiability; however, extracting coherent and accurate morphings from standard MLPs typically relies on costly regularizations, which often lead to unstable traini…

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models
Yankun Han
https://arxiv.org/abs/2510.09423 https://arxiv.org…

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models
Weight initialization governs signal propagation and gradient flow at the start of training. This paper offers a theory-grounded and empirically validated study across two regimes: compact ReLU multilayer perceptrons and GPT-2-style transformers. First, a logarithmic sweep of the initial standard deviation maps vanishing and exploding regimes and identifies a broad stability band with standard deviations between 1e-2 and 1e-1. Second, a controlled comparison shows that Kaiming (fan-in) initiali…

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems
Haoran He
https://arxiv.org/abs/2510.11891 https://ar…

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems
This paper proposes a machine learning-assisted channel estimation approach for massive MIMO systems, leveraging DNNs to outperform traditional LS and MMSE methods. In 5G and beyond, accurate channel estimation mitigates pilot contamination and high mobility issues that harm system reliability. The proposed DNN architecture includes multi-layer perceptrons with ReLU activation, 3 hidden layers (256, 128, 64 neurons respectively), uses Adam optimizer (learning rate 1e-4) and MSE loss function. I…

SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
Qihu Xie, Yuan Li, Yi Kang
https://arxiv.org/abs/2509.07373 https…

SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
Implicit neural representations have recently been extended to represent convolutional neural network weights via neural representation for neural networks, offering promising parameter compression benefits. However, standard multi-layer perceptrons used in neural representation for neural networks exhibit a pronounced spectral bias, hampering their ability to reconstruct high-frequency details effectively. In this paper, we propose SBS, a parameter-efficient enhancement to neural representatio…

Kolmogorov-Arnold Networks in Thermoelectric Materials Design
Marco Fronzi, Michael J. Ford, Kamal Singh Nayal, Olexandr Isayev, Catherine Stampfl
https://arxiv.org/abs/2510.02681

Kolmogorov-Arnold Networks in Thermoelectric Materials Design
The discovery of high-performance thermoelectric materials requires models that are both accurate and interpretable. Traditional machine learning approaches, while effective at property prediction, often act as black boxes and provide limited physical insight. In this work, we introduce Kolmogorov--Arnold Networks (KANs) for the prediction of thermoelectric properties, focusing on the Seebeck coefficient and band gap. Compared to multilayer perceptrons (MLPs), KANs achieve comparable predictive…

Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context
Andrejs Sorstkins, Josh Bailey, Dr Alistair Baron
https://arxiv.org/abs/2509.15366

Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context
The rapid evolution of neural architectures - from multilayer perceptrons to large-scale Transformer-based models - has enabled language models (LLMs) to exhibit emergent agentic behaviours when equipped with memory, planning, and external tool use. However, their inherent stochasticity and multi-step decision processes render classical evaluation methods inadequate for diagnosing agentic performance. This work introduces a diagnostic framework for expert systems that not only evaluates but als…

Physics-Informed Kolmogorov-Arnold Networks for multi-material elasticity problems in electronic packaging
Yanpeng Gong, Yida He, Yue Mei, Xiaoying Zhuang, Fei Qin, Timon Rabczuk
https://arxiv.org/abs/2508.16999

Physics-Informed Kolmogorov-Arnold Networks for multi-material elasticity problems in electronic packaging
This paper proposes a Physics-Informed Kolmogorov-Arnold Network (PIKAN) method for analyzing elasticity problems in electronic packaging multi-material structures. The core innovation lies in replacing Multi-Layer Perceptrons (MLPs) with Kolmogorov-Arnold Networks (KANs) within the energy-based Physics-Informed Neural Networks (PINNs) framework. The method constructs admissible displacement fields that automatically satisfy essential boundary conditions and employs various numerical integratio…

Fourier Feature Networks for High-Fidelity Prediction of Perturbed Optical Fields
Joshua R. Jandrell, Mitchell A. Cox
https://arxiv.org/abs/2508.19751 https://

Fourier Feature Networks for High-Fidelity Prediction of Perturbed Optical Fields
Modelling the effects of perturbations on optical fields often requires learning highly oscillatory complex-valued functions. Standard multi-layer perceptrons (MLPs) struggle with this task due to an inherent spectral bias, preventing them from fitting high-frequency sinusoids. To overcome this, we incorporate Fourier features - a set of predefined sinusoids dependent on the perturbation - as an additional network input. This reframes the learning problem from approximating a complex function t…

Are Neural Networks Collision Resistant?
Marco Benedetti, Andrej Bogdanov, Enrico M. Malatesta, Marc M\'ezard, Gianmarco Perrupato, Alon Rosen, Nikolaj I. Schwartzbach, Riccardo Zecchina
https://arxiv.org/abs/2509.20262

Are Neural Networks Collision Resistant?
When neural networks are trained to classify a dataset, one finds a set of weights from which the network produces a label for each data point. We study the algorithmic complexity of finding a collision in a single-layer neural net, where a collision is defined as two distinct sets of weights that assign the same labels to all data. For binary perceptrons with oscillating activation functions, we establish the emergence of an overlap gap property in the space of collisions. This is a topologica…

Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
Saman Yazdannik, Morteza Tayefi, Shamim Sanisales
https://arxiv.org/abs/2508.14536 https://arxiv.or…

Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
The performance of Deep Q-Networks (DQN) is critically dependent on the ability of its underlying neural network to accurately approximate the action-value function. Standard function approximators, such as multi-layer perceptrons, may struggle to efficiently represent the complex value landscapes inherent in many reinforcement learning problems. This paper introduces a novel architecture, the Chebyshev-DQN (Ch-DQN), which integrates a Chebyshev polynomial basis into the DQN framework to create…