Modeling Object Recognition in Newborn Chicks using Deep Neural Networks
This work addresses the origins of object recognition in newborn animals, offering a computational approach that is incremental in linking DNN models to controlled-rearing studies.
The study tackled the problem of understanding object recognition in newborn chicks by using unsupervised deep neural network features to predict their view-invariant recognition behavior, finding that these features made competitive predictions compared to supervised ones.
In recent years, the brain and cognitive sciences have made great strides developing a mechanistic understanding of object recognition in mature brains. Despite this progress, fundamental questions remain about the origins and computational foundations of object recognition. What learning algorithms underlie object recognition in newborn brains? Since newborn animals learn largely through unsupervised learning, we explored whether unsupervised learning algorithms can be used to predict the view-invariant object recognition behavior of newborn chicks. Specifically, we used feature representations derived from unsupervised deep neural networks (DNNs) as inputs to cognitive models of categorization. We show that features derived from unsupervised DNNs make competitive predictions about chick behavior compared to supervised features. More generally, we argue that linking controlled-rearing studies to image-computable DNN models opens new experimental avenues for studying the origins and computational basis of object recognition in newborn animals.