Evidence
Behav Brain Sci. 2023 Dec 6;46:e394. doi: 10.1017/S0140525X23001516.
ABSTRACT
Bowers et al. express skepticism about deep neural networks (DNNs) as models of human vision due to DNNs’ failures to account for results from psychological research. We argue that to fairly assess DNNs, we must first train them on more human-like tasks which we hypothesize will induce more human-like behaviors and representations.
PMID:38054325 | DOI:10.1017/S0140525X23001516
Estimated reading time: 2 minute(s)
Latest: Psychiatryai.com #RAISR4D Evidence
Cool Evidence: Engaging Young People and Students in Real-World Evidence
Real-Time Evidence Search [Psychiatry]
AI Research
For human-like models, train on human-like tasks
🌐 90 Days
AI Virtual Reality Related Evidence Matrix
Evidence Blueprint
For human-like models, train on human-like tasks
☊ AI-Driven Related Evidence Nodes
(recent articles with at least 5 words in title)
More Evidence
For human-like models, train on human-like tasks
🌐 365 Days
AI Virtual Reality Related Evidence Matrix
