In the field of artificial intelligence, agents learn how to take decisions by fitting their parameters on a set of samples called training set. Similarly, a core set is a subset of the training samples such that, if an agent exploits this set to fit its parameters instead of the whole training set, then the quality of the inferences does not change significantly. Relaxing the constraint that restricts the search for core sets to the available data, neural networks may be used to generate virtual samples, called archetype set, containing the same kind of information. This work illustrates the features of GH-ARCH, a recently proposed self-organizing hierarchical neural network for archetype discovery. Experiments show how the use of archetypes allows both ML agents to make fast and accurate predictions and human experts to make sense of such decisions by analyzing few important samples.

Generating Neural Archetypes to Instruct Fast and Interpretable Decisions / Barbiero, Pietro; Ciravegna, Gabriele; Cirrincione, Giansalvo; Tonda, Alberto; Squillero, Giovanni. - STAMPA. - 1009:(2020), pp. 45-52. ((Intervento presentato al convegno The International Conference on Decision Economics [10.1007/978-3-030-38227-8_6].

Generating Neural Archetypes to Instruct Fast and Interpretable Decisions

Squillero, Giovanni
2020

Abstract

In the field of artificial intelligence, agents learn how to take decisions by fitting their parameters on a set of samples called training set. Similarly, a core set is a subset of the training samples such that, if an agent exploits this set to fit its parameters instead of the whole training set, then the quality of the inferences does not change significantly. Relaxing the constraint that restricts the search for core sets to the available data, neural networks may be used to generate virtual samples, called archetype set, containing the same kind of information. This work illustrates the features of GH-ARCH, a recently proposed self-organizing hierarchical neural network for archetype discovery. Experiments show how the use of archetypes allows both ML agents to make fast and accurate predictions and human experts to make sense of such decisions by analyzing few important samples.
978-3-030-38226-1
978-3-030-38227-8
File in questo prodotto:
File Dimensione Formato  
2019 decon.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.86 MB
Formato Adobe PDF
1.86 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Generating_Neural_Archetypes_to_Instruct_Fast_and_Interpretable_Decisions.pdf

embargo fino al 08/02/2021

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 743.3 kB
Formato Adobe PDF
743.3 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2792951