Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · cs/0412023

Multidimensional data classification with artificial neural networks

P. Boinee·F. Barbarino·A. De Angelis
View original source ↗Read source document ↗Export metadata ↓

Abstract

Multi-dimensional data classification is an important and challenging problem in many astro-particle experiments. Neural networks have proved to be versatile and robust in multi-dimensional data classification. In this article we shall study the classification of gamma from the hadrons for the MAGIC Experiment. Two neural networks have been used for the classification task. One is Multi-Layer Perceptron based on supervised learning and other is Self-Organising Map (SOM), which is based on unsupervised learning technique. The results have been shown and the possible ways of combining these networks have been proposed to yield better and faster classification results.

Explore related subjects

cs.NEcs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

P. Boinee, F. Barbarino, A. De Angelis. 2004-12-06. Multidimensional data classification with artificial neural networks. https://arxiv.org/abs/cs/0412023

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

GC-LIF: Spiking Group-Equivariant Neural Network With Group-Coupled Membrane Dynamics

Spiking neural networks (SNNs) promise event-driven, low-power inference, but on vision tasks they still acquire rotation invariance only through data augmentation. Group-equivariant CNNs build such symmetries into the architecture, yet a faithful spiking analogue is missing: a leaky integrate-and-fire (LIF) neuron placed after a $G$-equivariant convolution can break equivariance through its membrane recurrence. We give a necessary and sufficient condition for this not to happen. The layer is equivariant at every time step if and only if the neuron parameters $(β, v_{\mathrm{th}})$ are constant along the joint orbits of the group action on the (group, space) index. We solve it in closed form, and it covers any elementwise stateful neuron. Its sufficiency half specialises a known result for equivariant recurrent networks; its necessity half rules out the heterogeneous per-neuron parameters common in SNNs. The per-channel parameterisation that satisfies it, Group-Coupled LIF (GC-LIF), is combined with $p4$ and $p4m$-equivariant convolutions and a spike-rate group max-pool into SGE-Net. On MNIST, KMNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100, evaluating each checkpoint on the clean test set and all its group-transformed copies, SGE-Net trained without rotations is invariant under $C_4$ and $D_4$ and outperforms a plain SNN trained with rotations in nine of ten dataset-group pairs, whereas non-equivariant baselines lose up to $72$ percentage points in the worst case. Operator-level tests confirm the theory before and after training, and an analytical estimate places SGE-Net at $1.7\times$ the arithmetic energy of a standard CNN and $2.3\times$ below its ANN counterpart at eight time steps.

cs.NE↗
arXiv2026

Diagnosing Optimizer-Landscape Interaction via Representation in Subset Selection Multitasking: Evidence from Piano Fingering

Continuous relaxations are commonly used as an encoding scheme for evolutionary multitasking optimization (EMTO), allowing heterogeneous tasks to be optimized within a unified search space. However, these continuous representations fundamentally reshape the induced fitness landscape, and their impact on optimization behavior and knowledge transfer remains underexplored. In this work, we bridge the gap by analyzing the interaction between the representation-induced fitness landscape and optimizer behavior through fitness landscape analysis. Using piano fingering estimation as a representative case of the subset selection problem, we introduce several encoding variants and investigate how their induced landscapes influence search dynamics and solution quality under EMTO. Our analysis indicates that transfer efficacy is strongly associated with changes in representation-induced landscape characteristics, rather than algorithmic factors alone, highlighting the representation design as the key factor of effective knowledge transfer in multitasking optimization.

cs.NE↗
arXiv2026

HEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization

Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization (MOCO). Yet most methods evolve the operators while leaving the process that discovers them fixed. This limits adaptation as new Pareto trade-offs and operator interactions change where and how the search should proceed. We introduce HEMO, which makes the AOD harness itself a self-evolving optimization target. HEMO maintains a persistent harness state and updates one module at a time, revising the logic that determines which experience to retrieve, which operators to improve, which parents to select, and how to formulate the orchestration of search steps. Downstream solution quality and runtime guide these updates, while a discounted UCB scheduler directs adaptation toward promising modules as their utility changes. A persistent memory filesystem preserves candidate outcomes and diagnostic feedback across harness states, enabling successive states to build on accumulated optimization experience. Experiments across eight MOCO tasks and two structurally distinct evolutionary backbones demonstrate strong performance against conventional evolutionary, neural, and LLM-based AOD baselines, together with effective transfer to related tasks. HEMO extends automatic operator design beyond evolving individual operators to improving the search process that discovers them.

cs.NE↗