2 Contributo in Volume

2 Contributo in Volume: [16977] Home page macrotipologia

Sfoglia

Prodotti recenti

Interactive LLM-Assisted Curriculum Learning for Multi-Task Evolutionary Policy Search

Multi-task policy search is a challenging problem because policies are required to generalize beyond training cases. Curriculum learning has proven to be effective in this setting, as it introduces complexity progressively. However, designing effective curricula is labor-intensive and requires extensive domain expertise. LLM-based curriculum generation has only recently emerged as a potential solution, but was limited to operate in static, offline modes without leveraging real-time feedback f...

Extending Decision Predicate Graphs for Comprehensive Explanation of Isolation Forest

The need to explain predictive models is well-established in modern machine learning. However, beyond model interpretability, understanding pre-processing methods is equally essential. Understanding how data modifications impact model performance improvements and potential biases and promoting a reliable pipeline is mandatory for developing robust machine learning solutions. Isolation Forest (iForest) is a widely used technique for outlier detection that performs well. Its effectiveness incre...

Models of agency in AI ethics education

This paper presents two models of agency that offer useful frameworks for understanding both machine and human action. We explore these models by examining their philosophical foundations, relevant literature, and implications for AI ethics. We argue that engaging with these concepts in AI ethics education can help clarify the respective strengths and limitations of human and artificial agents, thereby supporting the development of more effective oversight strategies. The paper concludes with...

Graph-Conditional Flow Matching for Relational Data Generation

Data synthesis is gaining momentum as a privacy-enhancing technology. While single-table tabular data generation has seen considerable progress, current methods for multi-table data often lack the flexibility and expressiveness needed to capture complex relational structures. In particular, they struggle with long-range dependencies and complex foreign-key relationships, such as tables with multiple parent tables or multiple types of links between the same pair of tables. We propose a generat...

Diophantine Modeling of Provability in Algebraic Logic

It has long been established that the set Th of theorems in an axiomatic formal theory is recursively enumerable (r.e.). Building upon the Davis-Putnam-Robinson-Matiyasevich theorem, which states that every r.e. set is Diophantine, this paper explores the complexity of representing Th through a Diophantine equation 𝐷 = 0. We contend that a good trade-off between two primary measures of the complexity of the representation, which are the number of unknowns and the degree of the polynomial 𝐷,...

Scopri

Accesso al fulltext

no fulltext12044
reserved3415
open1331
partially open182
mixed2
embargoed1

ArTS Archivio della ricerca di Trieste