Convolutional neural networks as a model of the visual system: Past, present, and future
GW Lindsay - Journal of cognitive neuroscience, 2021 - direct.mit.edu
Convolutional neural networks (CNNs) were inspired by early findings in the study of
biological vision. They have since become successful tools in computer vision and state-of …
biological vision. They have since become successful tools in computer vision and state-of …
Deep learning: the good, the bad, and the ugly
T Serre - Annual review of vision science, 2019 - annualreviews.org
Artificial vision has often been described as one of the key remaining challenges to be
solved before machines can act intelligently. Recent developments in a branch of machine …
solved before machines can act intelligently. Recent developments in a branch of machine …
Building machines that learn and think like people
Recent progress in artificial intelligence has renewed interest in building systems that learn
and think like people. Many advances have come from using deep neural networks trained …
and think like people. Many advances have come from using deep neural networks trained …
Comparing deep neural networks against humans: object recognition when the signal gets weaker
Human visual object recognition is typically rapid and seemingly effortless, as well as largely
independent of viewpoint and object orientation. Until very recently, animate visual systems …
independent of viewpoint and object orientation. Until very recently, animate visual systems …
Many but not all deep neural network audio models capture brain responses and exhibit correspondence between model stages and brain regions
Models that predict brain responses to stimuli provide one measure of understanding of a
sensory system and have many potential applications in science and engineering. Deep …
sensory system and have many potential applications in science and engineering. Deep …
Evaluating (and improving) the correspondence between deep neural networks and human representations
Decades of psychological research have been aimed at modeling how people learn
features and categories. The empirical validation of these theories is often based on artificial …
features and categories. The empirical validation of these theories is often based on artificial …
Neural representational geometry underlies few-shot concept learning
B Sorscher, S Ganguli… - Proceedings of the …, 2022 - National Acad Sciences
Understanding the neural basis of the remarkable human cognitive capacity to learn novel
concepts from just one or a few sensory experiences constitutes a fundamental problem. We …
concepts from just one or a few sensory experiences constitutes a fundamental problem. We …
Capturing human categorization of natural images by combining deep networks and cognitive models
Human categorization is one of the most important and successful targets of cognitive
modeling, with decades of model development and assessment using simple, low …
modeling, with decades of model development and assessment using simple, low …
Deep learning reveals what vocal bursts express in different cultures
JA Brooks, P Tzirakis, A Baird, L Kim, M Opara… - Nature Human …, 2023 - nature.com
Human social life is rich with sighs, chuckles, shrieks and other emotional vocalizations,
called 'vocal bursts'. Nevertheless, the meaning of vocal bursts across cultures is only …
called 'vocal bursts'. Nevertheless, the meaning of vocal bursts across cultures is only …
Deep convolutional neural networks outperform feature-based but not categorical models in explaining object similarity judgments
Recent advances in Deep convolutional Neural Networks (DNNs) have enabled
unprecedentedly accurate computational models of brain representations, and present an …
unprecedentedly accurate computational models of brain representations, and present an …