Parallel development of object recognition in newborn chicks and deep neural networks

HIGHLIGHTS

• What: The authors propose that visual systems are space-time fitters meaning visual development can be understood as a blind fitting process (akin to evolution) in which visual systems gradually adapt to the spatiotemporal distributions in the newborn`s environment. The authors show that when deep neural networks (CNNs and transformers) are trained in the same visual environments as newborn chicks the models develop the same object recognition skills as chicks. The study shows that blind fitting processes (variation + selection learning) can mimic the rapid visual learning of precocial newborn animals in the absence of innate (hardcoded . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.