Mimicking the human brain to achieve human-level cognition performance has been a core challenge in artificial intelligence research for decades. Humans are very efficient in capturing the most important information while being exposed to a plethora of different stimuli, a capability that is used to represent and understand their surroundings in a concise fashion. Machine learning research has made considerable progress toward cloning such a human capability with innovative techniques like deep learning, feature learning, incremental learning, and so on. In this article, an overview of the mainstream brain-inspired architectures and research directions proposed over the past decade is provided. In addition, a novel architecture exploiting the strengths of the current methods is proposed. Preliminary results demonstrate that it is able to achieve state-of-the-art results in a more efficient way.

The Evolution of Neural Learning Systems: A Novel Architecture Combining the Strengths of NTs, CNNs, and ELMs

MARTINEL, Niki;MICHELONI, Christian;FORESTI, Gian Luca
2015-01-01

Abstract

Mimicking the human brain to achieve human-level cognition performance has been a core challenge in artificial intelligence research for decades. Humans are very efficient in capturing the most important information while being exposed to a plethora of different stimuli, a capability that is used to represent and understand their surroundings in a concise fashion. Machine learning research has made considerable progress toward cloning such a human capability with innovative techniques like deep learning, feature learning, incremental learning, and so on. In this article, an overview of the mainstream brain-inspired architectures and research directions proposed over the past decade is provided. In addition, a novel architecture exploiting the strengths of the current methods is proposed. Preliminary results demonstrate that it is able to achieve state-of-the-art results in a more efficient way.
File in questo prodotto:
File Dimensione Formato  
2015_SMCM_NeuralEvolution.pdf

non disponibili

Descrizione: Main document
Tipologia: Documento in Post-print
Licenza: Non pubblico
Dimensione 1 MB
Formato Adobe PDF
1 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11390/1087330
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact