Search Results for author: Samantha M. W. Wood

Found 4 papers, 1 papers with code

Object permanence in newborn chicks is robust against opposing evidence

no code implementations22 Feb 2024 Justin N. Wood, Tomer D. Ullman, Brian W. Wood, Elizabeth S. Spelke, Samantha M. W. Wood

Newborn animals have advanced perceptual skills at birth, but the nature of this initial knowledge is unknown.

Object

Are Vision Transformers More Data Hungry Than Newborn Visual Systems?

1 code implementation NeurIPS 2023 Lalit Pandey, Samantha M. W. Wood, Justin N. Wood

Thus, ViTs were not more data hungry than newborn visual systems: both learned view invariant object representations in impoverished visual environments.

Object Object Recognition

A newborn embodied Turing test for view-invariant object recognition

no code implementations8 Jun 2023 Denizhan Pak, Donsuk Lee, Samantha M. W. Wood, Justin N. Wood

Recent progress in artificial intelligence has renewed interest in building machines that learn like animals.

Object Recognition

Development of collective behavior in newborn artificial agents

no code implementations6 Nov 2021 Donsuk Lee, Samantha M. W. Wood, Justin N. Wood

Here, we used deep reinforcement learning and curiosity-driven learning -- two learning mechanisms deeply rooted in psychological and neuroscientific research -- to build newborn artificial agents that develop collective behavior.

Object Recognition reinforcement-learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.