Convolutional Neural Networks (CNN) are a class of machine learning models predominately used in computer vision tasks and can achieve human-like performance through learning from experience. Their striking similarities to the structural and functional principles of the primate visual system allow for comparisons between these artificial networks and their biological counterparts, enabling exploration of how visual functions and neural representations may emerge in the real brain from a limited set of computational principles. After considering the basic features of CNNs, we discuss the opportunities and challenges of endorsing CNNs as in silico models of the primate visual system. Specifically, we highlight several emerging notions about the anatomical and physiological properties of the visual system that still need to be systematically integrated into current CNN models. These tenets include the implementation of parallel processing pathways from the early stages of retinal input and the reconsideration of several assumptions concerning the serial progression of information flow. We suggest design choices and architectural constraints that could facilitate a closer alignment with biology provide causal evidence of the predictive link between the artificial and biological visual systems. Adopting this principled perspective could potentially lead to new research questions and applications of CNNs beyond modeling object recognition.

Convolutional neural networks for vision neuroscience: significance, developments, and outstanding issues

Celeghin, Alessia
Co-first
;
Borriero, Alessio
Co-first
;
Orsenigo, Davide;Diano, Matteo;Perotti, Alan;Petri, Giovanni;Tamietto, Marco
Last
2023-01-01

Abstract

Convolutional Neural Networks (CNN) are a class of machine learning models predominately used in computer vision tasks and can achieve human-like performance through learning from experience. Their striking similarities to the structural and functional principles of the primate visual system allow for comparisons between these artificial networks and their biological counterparts, enabling exploration of how visual functions and neural representations may emerge in the real brain from a limited set of computational principles. After considering the basic features of CNNs, we discuss the opportunities and challenges of endorsing CNNs as in silico models of the primate visual system. Specifically, we highlight several emerging notions about the anatomical and physiological properties of the visual system that still need to be systematically integrated into current CNN models. These tenets include the implementation of parallel processing pathways from the early stages of retinal input and the reconsideration of several assumptions concerning the serial progression of information flow. We suggest design choices and architectural constraints that could facilitate a closer alignment with biology provide causal evidence of the predictive link between the artificial and biological visual systems. Adopting this principled perspective could potentially lead to new research questions and applications of CNNs beyond modeling object recognition.
2023
17
1
13
Convolutional Neural Networks (CNN); V1-independent vision; blindsight; pulvinar; superior colliculus; ventral stream; visual system
Celeghin, Alessia; Borriero, Alessio; Orsenigo, Davide; Diano, Matteo; Méndez Guerrero, Carlos Andrés; Perotti, Alan; Petri, Giovanni; Tamietto, Marco...espandi
File in questo prodotto:
File Dimensione Formato  
fncom-17-1153572.pdf

Accesso aperto

Descrizione: Celeghin et al., fncom, 2023
Tipo di file: PDF EDITORIALE
Dimensione 1.86 MB
Formato Adobe PDF
1.86 MB Adobe PDF Visualizza/Apri

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/2318/1931932
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 3
social impact