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 …
A spectral theory of neural prediction and alignment
The representations of neural networks are often compared to those of biological systems by
performing regression between the neural network responses and those measured from …
performing regression between the neural network responses and those measured from …
Large-scale calcium imaging reveals a systematic V4 map for encoding natural scenes
Biological visual systems have evolved to process natural scenes. A full understanding of
visual cortical functions requires a comprehensive characterization of how neuronal …
visual cortical functions requires a comprehensive characterization of how neuronal …
Strong and precise modulation of human percepts via robustified ANNs
The visual object category reports of artificial neural networks (ANNs) are notoriously
sensitive to tiny, adversarial image perturbations. Because human category reports (aka …
sensitive to tiny, adversarial image perturbations. Because human category reports (aka …
Many but not all deep neural network audio models capture brain responses and exhibit correspondence between model stages and brain regions
D Boebinger, JH McDermott - PLoS Biology, 2023 - search.proquest.com
Abstract Models that predict brain responses to stimuli provide one measure of
understanding of a sensory system and have many potential applications in science and …
understanding of a sensory system and have many potential applications in science and …
Layerwise complexity-matched learning yields an improved model of cortical area V2
Human ability to recognize complex visual patterns arises through transformations
performed by successive areas in the ventral visual cortex. Deep neural networks trained …
performed by successive areas in the ventral visual cortex. Deep neural networks trained …
DeepSpeech models show Human-like Performance and Processing of Cochlear Implant Inputs
Cochlear implants (CIs) are arguably the most successful neural implant, having restored
hearing to over one million people worldwide. While CI research has focused on modeling …
hearing to over one million people worldwide. While CI research has focused on modeling …
Spectral regularization for adversarially-robust representation learning
The vulnerability of neural network classifiers to adversarial attacks is a major obstacle to
their deployment in safety-critical applications. Regularization of network parameters during …
their deployment in safety-critical applications. Regularization of network parameters during …
Quantum-tunnelling deep neural networks for sociophysical neuromorphic AI
IS Maksymov - arXiv preprint arXiv:2407.11013, 2024 - arxiv.org
The discovery of the quantum tunnelling effect--the transmission of particles through a high
potential barrier--was one of the most impressive achievements of quantum mechanics …
potential barrier--was one of the most impressive achievements of quantum mechanics …
[HTML][HTML] Quantum-tunneling deep neural network for optical illusion recognition
IS Maksymov - APL Machine Learning, 2024 - pubs.aip.org
The discovery of the quantum tunneling (QT) effect—the transmission of particles through a
high potential barrier—was one of the most impressive achievements of quantum mechanics …
high potential barrier—was one of the most impressive achievements of quantum mechanics …