Extreme image transformations affect humans and machines differently
Biol Cybern. 2023 Jun 13. doi: 10.1007/s00422-023-00968-7. Online ahead of print.ABSTRACTSome recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evalua...
Source: Biological Cybernetics - June 13, 2023 Category: Science Authors: Girik Malik Dakarai Crowder Ennio Mingolla Source Type: research
Extreme image transformations affect humans and machines differently
Biol Cybern. 2023 Jun 13. doi: 10.1007/s00422-023-00968-7. Online ahead of print.ABSTRACTSome recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evalua...
Source: Biological Cybernetics - June 13, 2023 Category: Science Authors: Girik Malik Dakarai Crowder Ennio Mingolla Source Type: research
Extreme image transformations affect humans and machines differently
Biol Cybern. 2023 Jun 13. doi: 10.1007/s00422-023-00968-7. Online ahead of print.ABSTRACTSome recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evalua...
Source: Biological Cybernetics - June 13, 2023 Category: Science Authors: Girik Malik Dakarai Crowder Ennio Mingolla Source Type: research
Extreme image transformations affect humans and machines differently
Biol Cybern. 2023 Jun 13. doi: 10.1007/s00422-023-00968-7. Online ahead of print.ABSTRACTSome recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evalua...
Source: Biological Cybernetics - June 13, 2023 Category: Science Authors: Girik Malik Dakarai Crowder Ennio Mingolla Source Type: research
Extreme image transformations affect humans and machines differently
Biol Cybern. 2023 Jun 13. doi: 10.1007/s00422-023-00968-7. Online ahead of print.ABSTRACTSome recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evalua...
Source: Biological Cybernetics - June 13, 2023 Category: Science Authors: Girik Malik Dakarai Crowder Ennio Mingolla Source Type: research
Extreme image transformations affect humans and machines differently
Biol Cybern. 2023 Jun 13. doi: 10.1007/s00422-023-00968-7. Online ahead of print.ABSTRACTSome recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evalua...
Source: Biological Cybernetics - June 13, 2023 Category: Science Authors: Girik Malik Dakarai Crowder Ennio Mingolla Source Type: research
Canonical circuit computations for computer vision
Biol Cybern. 2023 Jun 12. doi: 10.1007/s00422-023-00966-9. Online ahead of print.ABSTRACTAdvanced computer vision mechanisms have been inspired by neuroscientific findings. However, with the focus on improving benchmark achievements, technical solutions have been shaped by application and engineering constraints. This includes the training of neural networks which led to the development of feature detectors optimally suited to the application domain. However, the limitations of such approaches motivate the need to identify computational principles, or motifs, in biological vision that can enable further foundational advanc...
Source: Biological Cybernetics - June 12, 2023 Category: Science Authors: Daniel Schmid Christian Jarvers Heiko Neumann Source Type: research
Canonical circuit computations for computer vision
Biol Cybern. 2023 Jun 12. doi: 10.1007/s00422-023-00966-9. Online ahead of print.ABSTRACTAdvanced computer vision mechanisms have been inspired by neuroscientific findings. However, with the focus on improving benchmark achievements, technical solutions have been shaped by application and engineering constraints. This includes the training of neural networks which led to the development of feature detectors optimally suited to the application domain. However, the limitations of such approaches motivate the need to identify computational principles, or motifs, in biological vision that can enable further foundational advanc...
Source: Biological Cybernetics - June 12, 2023 Category: Science Authors: Daniel Schmid Christian Jarvers Heiko Neumann Source Type: research
How aggressive interactions with biomimetic agents optimize reproductive performances in mass-reared males of the Mediterranean fruit fly
This study adds fundamental knowledge on the potential role of specific neuro-behavioural processes in the ecology of tephritid species and paves the way to innovative biotechnological control methods based on robotics and bionics.PMID:37256317 | DOI:10.1007/s00422-023-00965-w (Source: Biological Cybernetics)
Source: Biological Cybernetics - May 31, 2023 Category: Science Authors: Donato Romano Giovanni Benelli Cesare Stefanini Source Type: research
How aggressive interactions with biomimetic agents optimize reproductive performances in mass-reared males of the Mediterranean fruit fly
This study adds fundamental knowledge on the potential role of specific neuro-behavioural processes in the ecology of tephritid species and paves the way to innovative biotechnological control methods based on robotics and bionics.PMID:37256317 | DOI:10.1007/s00422-023-00965-w (Source: Biological Cybernetics)
Source: Biological Cybernetics - May 31, 2023 Category: Science Authors: Donato Romano Giovanni Benelli Cesare Stefanini Source Type: research
How aggressive interactions with biomimetic agents optimize reproductive performances in mass-reared males of the Mediterranean fruit fly
This study adds fundamental knowledge on the potential role of specific neuro-behavioural processes in the ecology of tephritid species and paves the way to innovative biotechnological control methods based on robotics and bionics.PMID:37256317 | DOI:10.1007/s00422-023-00965-w (Source: Biological Cybernetics)
Source: Biological Cybernetics - May 31, 2023 Category: Science Authors: Donato Romano Giovanni Benelli Cesare Stefanini Source Type: research
How aggressive interactions with biomimetic agents optimize reproductive performances in mass-reared males of the Mediterranean fruit fly
This study adds fundamental knowledge on the potential role of specific neuro-behavioural processes in the ecology of tephritid species and paves the way to innovative biotechnological control methods based on robotics and bionics.PMID:37256317 | DOI:10.1007/s00422-023-00965-w (Source: Biological Cybernetics)
Source: Biological Cybernetics - May 31, 2023 Category: Science Authors: Donato Romano Giovanni Benelli Cesare Stefanini Source Type: research
How aggressive interactions with biomimetic agents optimize reproductive performances in mass-reared males of the Mediterranean fruit fly
This study adds fundamental knowledge on the potential role of specific neuro-behavioural processes in the ecology of tephritid species and paves the way to innovative biotechnological control methods based on robotics and bionics.PMID:37256317 | DOI:10.1007/s00422-023-00965-w (Source: Biological Cybernetics)
Source: Biological Cybernetics - May 31, 2023 Category: Science Authors: Donato Romano Giovanni Benelli Cesare Stefanini Source Type: research
How aggressive interactions with biomimetic agents optimize reproductive performances in mass-reared males of the Mediterranean fruit fly
This study adds fundamental knowledge on the potential role of specific neuro-behavioural processes in the ecology of tephritid species and paves the way to innovative biotechnological control methods based on robotics and bionics.PMID:37256317 | DOI:10.1007/s00422-023-00965-w (Source: Biological Cybernetics)
Source: Biological Cybernetics - May 31, 2023 Category: Science Authors: Donato Romano Giovanni Benelli Cesare Stefanini Source Type: research
How aggressive interactions with biomimetic agents optimize reproductive performances in mass-reared males of the Mediterranean fruit fly
This study adds fundamental knowledge on the potential role of specific neuro-behavioural processes in the ecology of tephritid species and paves the way to innovative biotechnological control methods based on robotics and bionics.PMID:37256317 | DOI:10.1007/s00422-023-00965-w (Source: Biological Cybernetics)
Source: Biological Cybernetics - May 31, 2023 Category: Science Authors: Donato Romano Giovanni Benelli Cesare Stefanini Source Type: research
