Towards biologically plausible convolutional networks
Convolutional networks are ubiquitous in deep learning. They are particularly useful for
images, as they reduce the number of parameters, reduce training time, and increase …
images, as they reduce the number of parameters, reduce training time, and increase …
Soft Matching Distance: A metric on neural representations that captures single-neuron tuning
M Khosla, AH Williams - … of UniReps: the First Workshop on …, 2024 - proceedings.mlr.press
Common measures of neural representational (dis) similarity are designed to be insensitive
to rotations and reflections of the neural activation space. Motivated by the premise that the …
to rotations and reflections of the neural activation space. Motivated by the premise that the …
Deep spiking neural networks with high representation similarity model visual pathways of macaque and mouse
Deep artificial neural networks (ANNs) play a major role in modeling the visual pathways of
primate and rodent. However, they highly simplify the computational properties of neurons …
primate and rodent. However, they highly simplify the computational properties of neurons …
The algonauts project 2021 challenge: How the human brain makes sense of a world in motion
The sciences of natural and artificial intelligence are fundamentally connected. Brain-
inspired human-engineered AI are now the standard for predicting human brain responses …
inspired human-engineered AI are now the standard for predicting human brain responses …
Modeling Visual Impairments with Artificial Neural Networks: a Review
We present an approach to bridge the gap between the computational models of human
vision and the clinical practice on visual impairments (VI). In a nutshell, we propose to …
vision and the clinical practice on visual impairments (VI). In a nutshell, we propose to …
Approaching human 3D shape perception with neurally mappable models
Humans effortlessly infer the 3D shape of objects. What computations underlie this ability?
Although various computational models have been proposed, none of them capture the …
Although various computational models have been proposed, none of them capture the …
Unveiling functions of the visual cortex using task-specific deep neural networks
The human visual cortex enables visual perception through a cascade of hierarchical
computations in cortical regions with distinct functionalities. Here, we introduce an AI-driven …
computations in cortical regions with distinct functionalities. Here, we introduce an AI-driven …
Making sense of the multiplicity and dynamics of navigational codes in the brain
Since the discovery of conspicuously spatially tuned neurons in the hippocampal formation
over 50 years ago, characterizing which, where, and how neurons encode navigationally …
over 50 years ago, characterizing which, where, and how neurons encode navigationally …
Spiking generative adversarial network with attention scoring decoding
Generative models based on neural networks present a substantial challenge within deep
learning. As it stands, such models are primarily limited to the domain of artificial neural …
learning. As it stands, such models are primarily limited to the domain of artificial neural …
Personalized visual encoding model construction with small data
Quantifying population heterogeneity in brain stimuli-response mapping may allow insight
into variability in bottom-up neural systems that can in turn be related to individual's behavior …
into variability in bottom-up neural systems that can in turn be related to individual's behavior …