arXiv subjects

Roberto Hirata Jr

Publications and source records attributed to Roberto Hirata Jr.

5 recordsLinked to original sources

arXiv2026

Graph Memory: A Structured and Interpretable Framework for Modality-Agnostic Embedding-Based Inference

We introduce Graph Memory (GM), a structured non-parametric framework that represents an embedding space through a compact graph of reliability-annotated prototype regions. GM encodes local geometry and regional ambiguity through prototype relations and performs inference by diffusing query evidence across this structure, unifying instance retrieval, prototype-based reasoning, and graph diffusion within a single inductive and interpretable model. The framework is inherently modality-agnostic: in multimodal settings, independent prototype graphs are constructed for each modality and their calibrated predictions are combined through reliability-aware late fusion, enabling transparent integration of heterogeneous sources such as whole-slide images and gene-expression profiles. Experiments on synthetic benchmarks, breast histopathology (IDC), and the multimodal AURORA dataset show that GM matches or exceeds the accuracy of kNN and Label Spreading while providing substantially better calibration, smoother decision boundaries, and an order-of-magnitude smaller memory footprint. By explicitly modeling regional reliability and relational structure, GM offers a principled and interpretable approach to non-parametric inference across single- and multi-modal domains.

cs.LG↗

arXiv2019

Greenery Segmentation In Urban Images By Deep Learning

Vegetation is a relevant feature in the urban scenery and its awareness can be measured in an image by the Green View Index (GVI). Previous approaches to estimate the GVI were based upon heuristics image processing approaches and recently by deep learning networks (DLN). By leveraging some recent DLN architectures tuned to the image segmentation problem and exploiting a weighting strategy in the loss function (LF) we improved previously reported results in similar datasets.

cs.CV↗

arXiv2019

A logical-based corpus for cross-lingual evaluation

At present, different deep learning models are presenting high accuracy on popular inference datasets such as SNLI, MNLI, and SciTail. However, there are different indicators that those datasets can be exploited by using some simple linguistic patterns. This fact poses difficulties to our understanding of the actual capacity of machine learning models to solve the complex task of textual inference. We propose a new set of syntactic tasks focused on contradiction detection that require specific capacities over linguistic logical forms such as: Boolean coordination, quantifiers, definite description, and counting operators. We evaluate two kinds of deep learning models that implicitly exploit language structure: recurrent models and the Transformer network BERT. We show that although BERT is clearly more efficient to generalize over most logical forms, there is space for improvement when dealing with counting operators. Since the syntactic tasks can be implemented in different languages, we show a successful case of cross-lingual transfer learning between English and Portuguese.

cs.CL↗

arXiv2019

Kernels on fuzzy sets: an overview

This paper introduces the concept of kernels on fuzzy sets as a similarity measure for $[0,1]$-valued functions, a.k.a. \emph{membership functions of fuzzy sets}. We defined the following classes of kernels: the cross product, the intersection, the non-singleton and the distance-based kernels on fuzzy sets. Applicability of those kernels are on machine learning and data science tasks where uncertainty in data has an ontic or epistemistic interpretation.

cs.LG↗

arXiv2015

maigesPack: A Computational Environment for Microarray Data Analysis

Microarray technology is still an important way to assess gene expression in molecular biology, mainly because it measures expression profiles for thousands of genes simultaneously, what makes this technology a good option for some studies focused on systems biology. One of its main problem is complexity of experimental procedure, presenting several sources of variability, hindering statistical modeling. So far, there is no standard protocol for generation and evaluation of microarray data. To mitigate the analysis process this paper presents an R package, named maigesPack, that helps with data organization. Besides that, it makes data analysis process more robust, reliable and reproducible. Also, maigesPack aggregates several data analysis procedures reported in literature, for instance: cluster analysis, differential expression, supervised classifiers, relevance networks and functional classification of gene groups or gene networks.

stat.CO↗