While Machine Learning (ML) techniques enjoyed growing popularity in recent years, the role of Evolutionary Algorithms in this field is still marginal — quite a surprising fact considering how deeply the origins of the two fields are related. In this tutorial we present success stories of EAs exploited in specific ML tasks, such as feature selection, adversarial ML, whitebox modeling, also mentioning the renowned neuroevolution. We show how similar concepts appear in both fields with different names. At the same time, we show well-known and emerging challenges that EAs need to overcome to become widely adopted in ML. For instance, a reduced ability to scale or a general distrust toward stochasticity. Finally, we point out opportunities arising for new research lines, that play on the strengths of EAs, such as potential improvements over currently-used optimization techniques; and the capability to go beyond simple model fitting, creating solutions that expand over the boundaries of the training data.
Evolutionary algorithms and machine learning: Synergies, Challenges and Opportunities / Squillero, G.; Tonda, A.. - STAMPA. - (2020), pp. 1190-1205. (Intervento presentato al convegno 2020 Genetic and Evolutionary Computation Conference, GECCO 2020 tenutosi a mex nel 2020) [10.1145/3377929.3389863].
Evolutionary algorithms and machine learning: Synergies, Challenges and Opportunities
Squillero G.;
2020
Abstract
While Machine Learning (ML) techniques enjoyed growing popularity in recent years, the role of Evolutionary Algorithms in this field is still marginal — quite a surprising fact considering how deeply the origins of the two fields are related. In this tutorial we present success stories of EAs exploited in specific ML tasks, such as feature selection, adversarial ML, whitebox modeling, also mentioning the renowned neuroevolution. We show how similar concepts appear in both fields with different names. At the same time, we show well-known and emerging challenges that EAs need to overcome to become widely adopted in ML. For instance, a reduced ability to scale or a general distrust toward stochasticity. Finally, we point out opportunities arising for new research lines, that play on the strengths of EAs, such as potential improvements over currently-used optimization techniques; and the capability to go beyond simple model fitting, creating solutions that expand over the boundaries of the training data.File | Dimensione | Formato | |
---|---|---|---|
3377929.3389863.pdf
accesso aperto
Descrizione: Slide tutorial
Tipologia:
Altro materiale allegato
Licenza:
Creative commons
Dimensione
2.2 MB
Formato
Adobe PDF
|
2.2 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2843654