article

• Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT
• An ecologically motivated image dataset for deep learning yields better models of human vision
• Beware the beginnings: intermediate and higher-level representations in deep neural networks are strongly affected by weight initialisation.
• Deep Neural Networks in Computational Neuroscience
• Deep neural networks and visuo-semantic models explain complementary components of human ventral-stream representational dynamics
• Deep neural networks in computational neuroscience
• Diverse deep neural networks all predict human IT well, after training and fitting
• Extensive training leads to temporal and spatial shifts of cortical activity underlying visual category selectivity
• From photos to sketches - how humans and deep neural networks process objects across different levels of visual abstraction
• Individual differences among deep neural network models
• Individual differences among deep neural network models
• Modelling Human Visual Uncertainty using Bayesian Deep Neural Networks
• Predictive coding is a consequence of energy efficiency in recurrent neural networks
• Recurrence is required to capture the representational dynamics of the human visual system
• Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision
• Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision
• Representational dynamics in the human ventral stream captured in deep recurrent neural nets.
• Wild lab: A naturalistic free viewing experiment reveals previously unknown EEG signatures of face processing