[HTML][HTML] Using artificial neural networks to ask 'why'questions of minds and brains

N Kanwisher, M Khosla, K Dobs - Trends in Neurosciences, 2023 - cell.com
Neuroscientists have long characterized the properties and functions of the nervous system,
and are increasingly succeeding in answering how brains perform the tasks they do. But the …

Digital twin studies for reverse engineering the origins of visual intelligence

JN Wood, L Pandey, SMW Wood - Annual Review of Vision …, 2024 - annualreviews.org
What are the core learning algorithms in brains? Nativists propose that intelligence emerges
from innate domain-specific knowledge systems, whereas empiricists propose that …

Visual anagrams: Generating multi-view optical illusions with diffusion models

D Geng, I Park, A Owens - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
We address the problem of synthesizing multi-view optical illusions: images that change
appearance upon a transformation such as a flip or rotation. We propose a simple zero-shot …

Impact of colour on robustness of deep neural networks

K De, M Pedersen - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Convolutional neural networks have become the most widely used tool for computer vision
applications like image classification, segmentation, object localization etc. Recent studies …

IllusionVQA: A challenging optical illusion dataset for vision language models

HS Shahgir, KS Sayeed, A Bhattacharjee… - ar** biological and artificial intelligences
AH Taylor, APM Bastos, RL Brown, C Allen - Trends in Cognitive Sciences, 2022 - cell.com
Making inferences from behaviour to cognition is problematic due to a many-to-one map**
problem, in which any one behaviour can be generated by multiple possible cognitive …