Imagen de Portada
Código QR

Can We Read Neural Networks? Epistemic Implications of Two Historical Computer Science Papers.

The article discusses two computer science research papers concerning artificial intelligence (AI). Topics explored include the susceptibility of deep convolutional neural networks to input pertubations acknowledged in the 2013 study "Intriguing Properties of Neural Networks," by Christian Szegedy a...

Descripción completa

Publicado en:American Literature Vol. 95; no. 2; pp. 423 - 429
Autor principal: Offert, Fabian
Formato: Artículo
Publicado: Duke University Press Jun2023
Materias:
Computer science research
Artificial intelligence
Artificial neural networks
Language models
Computer programming
21st century (Literary period)
Acceso en línea:Ver este registro en EBSCOhost
Sumario:The article discusses two computer science research papers concerning artificial intelligence (AI). Topics explored include the susceptibility of deep convolutional neural networks to input pertubations acknowledged in the 2013 study "Intriguing Properties of Neural Networks," by Christian Szegedy and colleagues, and the capability of sequence-to-sequence language models to execute short computer programs reported in the 2014 study "Learning to Execute," by Wojciech Zaremba and Ilya Sutskever.