Tootfinder

Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset
Nabeyou Tadessa, Balaji Iyangar, Mashrur Chowdhury
https://arxiv.org/abs/2509.06835

Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset
Adversarial attacks pose significant threats to machine learning models by introducing carefully crafted perturbations that cause misclassification. While prior work has primarily focused on MNIST and similar datasets, this paper investigates the vulnerability of traffic sign classifiers using the LISA Traffic Sign dataset. We train a convolutional neural network to classify 47 different traffic signs and evaluate its robustness against Fast Gradient Sign Method (FGSM) and Projected Gradient De…

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
Andreas Maurer, Erfan Mirzaei, Massimiliano Pontil
https://arxiv.org/abs/2510.06028 https…

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
The paper provides data-dependent bounds on the test error of the Gibbs algorithm in the overparameterized interpolation regime, where low training errors are also obtained for impossible data, such as random labels in classification. The bounds are stable under approximation with Langevin Monte Carlo algorithms. Experiments on the MNIST and CIFAR-10 datasets verify that the bounds yield nontrivial predictions on true labeled data and correctly upper bound the test error for random labels. Our …

Boos of Donald Trump heard on ABC's broadcast of US Open. Good (Nancy Armour/USA Today)
https://www.usatoday.com/story/sports/columnist/nancy-armour/2025/09/07/abc-espn-air-boos-donald-trump-us-open/86031530007/
http://www.memeorandum.com/250907/p77#a250907p77

Inferring the Graph Structure of Images for Graph Neural Networks
Mayur S Gowda, John Shi, Augusto Santos, Jos\'e M. F. Moura
https://arxiv.org/abs/2509.04677 https://

Inferring the Graph Structure of Images for Graph Neural Networks
Image datasets such as MNIST are a key benchmark for testing Graph Neural Network (GNN) architectures. The images are traditionally represented as a grid graph with each node representing a pixel and edges connecting neighboring pixels (vertically and horizontally). The graph signal is the values (intensities) of each pixel in the image. The graphs are commonly used as input to graph neural networks (e.g., Graph Convolutional Neural Networks (Graph CNNs) [1, 2], Graph Attention Networks (GAT) […

Comparative Analysis of Novel NIRMAL Optimizer Against Adam and SGD with Momentum
Nirmal Gaud, Surej Mouli, Preeti Katiyar, Vaduguru Venkata Ramya
https://arxiv.org/abs/2508.04293

Comparative Analysis of Novel NIRMAL Optimizer Against Adam and SGD with Momentum
This study proposes NIRMAL (Novel Integrated Robust Multi-Adaptation Learning), a novel optimization algorithm that combines multiple strategies inspired by the movements of the chess piece. These strategies include gradient descent, momentum, stochastic perturbations, adaptive learning rates, and non-linear transformations. We carefully evaluated NIRMAL against two widely used and successful optimizers, Adam and SGD with Momentum, on four benchmark image classification datasets: MNIST, Fashion…

Transfer entropy and O-information to detect grokking in tensor network multi-class classification problems
Domenico Pomarico, Roberto Cilli, Alfonso Monaco, Loredana Bellantuono, Marianna La Rocca, Tommaso Maggipinto, Giuseppe Magnifico, Marlis Ontivero Ortega, Ester Pantaleo, Sabina Tangaro, Sebastiano Stramaglia, Roberto Bellotti, Nicola Amoroso
https://

Transfer entropy and O-information to detect grokking in tensor network multi-class classification problems
Quantum-enhanced machine learning, encompassing both quantum algorithms and quantum-inspired classical methods such as tensor networks, offers promising tools for extracting structure from complex, high-dimensional data. In this work, we study the training dynamics of Matrix Product State (MPS) classifiers applied to three-class problems, using both fashion MNIST and hyper-spectral satellite imagery as representative datasets. We investigate the phenomenon of grokking, where generalization emer…

SFATTI: Spiking FPGA Accelerator for Temporal Task-driven Inference -- A Case Study on MNIST
Alessio Caviglia, Filippo Marostica, Alessio Carpegna, Alessandro Savino, Stefano Di Carlo
https://arxiv.org/abs/2507.10561

SFATTI: Spiking FPGA Accelerator for Temporal Task-driven Inference -- A Case Study on MNIST
Hardware accelerators are essential for achieving low-latency, energy-efficient inference in edge applications like image recognition. Spiking Neural Networks (SNNs) are particularly promising due to their event-driven and temporally sparse nature, making them well-suited for low-power Field Programmable Gate Array (FPGA)-based deployment. This paper explores using the open-source Spiker+ framework to generate optimized SNNs accelerators for handwritten digit recognition on the MNIST dataset. S…

Comparing Contrastive and Triplet Loss in Audio-Visual Embedding: Intra-Class Variance and Greediness Analysis
Donghuo Zeng
https://arxiv.org/abs/2510.02161 https://

Comparing Contrastive and Triplet Loss in Audio-Visual Embedding: Intra-Class Variance and Greediness Analysis
Contrastive loss and triplet loss are widely used objectives in deep metric learning, yet their effects on representation quality remain insufficiently understood. We present a theoretical and empirical comparison of these losses, focusing on intra- and inter-class variance and optimization behavior (e.g., greedy updates). Through task-specific experiments with consistent settings on synthetic data and real datasets-MNIST, CIFAR-10-it is shown that triplet loss preserves greater variance within…

A Hybrid Multi-Well Hopfield-CNN with Feature Extraction and K-Means for MNIST Classification
Ahmed Farooq
https://arxiv.org/abs/2507.08766 https://…

A Hybrid Multi-Well Hopfield-CNN with Feature Extraction and K-Means for MNIST Classification
This study presents a hybrid model for classifying handwritten digits in the MNIST dataset, combining convolutional neural networks (CNNs) with a multi-well Hopfield network. The approach employs a CNN to extract high-dimensional features from input images, which are then clustered into class-specific prototypes using k-means clustering. These prototypes serve as attractors in a multi-well energy landscape, where a Hopfield network performs classification by minimizing an energy function that b…

Microscale optoelectronic reservoir networks of halide perovskite for in-sensor computing
Jeroen J. de Boer, Agustin O. Alvarez, Moritz C. Schmidt, Bruno Ehrler
https://arxiv.org/abs/2508.19916

Microscale optoelectronic reservoir networks of halide perovskite for in-sensor computing
Physical reservoir computing is a promising framework for efficient neuromorphic in and near-sensor computing applications. Here, we demonstrate a multimodal optoelectronic reservoir network based on halide perovskite semiconductor devices, capable of processing both voltage and light inputs. The devices consist of micrometer-sized, asymmetric crossbars covered with a MAPbI3 perovskite film. In a network, we simulate the performance by transforming MNIST images and videos based on the NMNIST da…

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi
https://arxiv.org/abs/2509.21341

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
We study symbolic surrogate modeling of frozen Transformer embeddings to obtain compact, auditable classifiers with calibrated probabilities. For five benchmarks (SST2G, 20NG, MNIST, CIFAR10, MSC17), embeddings from ModernBERT, DINOv2, and SigLIP are partitioned on the training set into disjoint, information-preserving views via semantic-preserving feature partitioning (SPFP). A cooperative multi-population genetic program (MEGP) then learns additive, closed-form logit programs over these views…

Improving Diagnostic Accuracy of Pigmented Skin Lesions With CNNs: an Application on the DermaMNIST Dataset
Nerma Kadric, Amila Akagic, Medina Kapo
https://arxiv.org/abs/2507.12961

Improving Diagnostic Accuracy of Pigmented Skin Lesions With CNNs: an Application on the DermaMNIST Dataset
Pigmented skin lesions represent localized areas of increased melanin and can indicate serious conditions like melanoma, a major contributor to skin cancer mortality. The MedMNIST v2 dataset, inspired by MNIST, was recently introduced to advance research in biomedical imaging and includes DermaMNIST, a dataset for classifying pigmented lesions based on the HAM10000 dataset. This study assesses ResNet-50 and EfficientNetV2L models for multi-class classification using DermaMNIST, employing transf…

Tangma: A Tanh-Guided Activation Function with Learnable Parameters
Shreel Golwala
https://arxiv.org/abs/2507.10560 https://arxiv.org…

Tangma: A Tanh-Guided Activation Function with Learnable Parameters
Activation functions are key to effective backpropagation and expressiveness in deep neural networks. This work introduces Tangma, a new activation function that combines the smooth shape of the hyperbolic tangent with two learnable parameters: $α$, which shifts the curve's inflection point to adjust neuron activation, and $γ$, which adds linearity to preserve weak gradients and improve training stability. Tangma was evaluated on MNIST and CIFAR-10 using custom networks composed of convolutio…

Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures
Siyu Yu, Zihan Qin, Tingshan Liu, Beiya Xu, R. Jacob Vogelstein, Jason Brown, Joshua T. Vogelstein
https://arxiv.org/abs/2507.10951

Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures
The complete connectome of the Drosophila larva brain offers a unique opportunity to investigate whether biologically evolved circuits can support artificial intelligence. We convert this wiring diagram into a Biological Processing Unit (BPU), a fixed recurrent network derived directly from synaptic connectivity. Despite its modest size 3,000 neurons and 65,000 weights between them), the unmodified BPU achieves 98% accuracy on MNIST and 58% on CIFAR-10, surpassing size-matched MLPs. Scaling the…