Shared visual illusions between humans and artificial neural networks

Benjamin, Ari S.; Qiu, Cheng; Zhang, Ling-Qi; Körding, Konrad P.; Stocker, Alan A.

doi:10.32470/ccn.2019.1299-0

Cited by 21 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1b). This finding recapitulates our preliminary findings and concurrent work of colleagues, and points to an origin in image statistics (Benjamin et al, 2019; Henderson and Serences, 2021). However, we also found that networks trained on rotated images do partially retain sensitivity to cardinal orientations; they do not simply rotate their sensitivity by 45º (SI Fig.…”

Section: Resultssupporting

confidence: 92%

“…We examine two model systems. First, we show that deep artificial networks trained on natural image classification show similar patterns of sensitivity as humans, and that this is a partly a consequence of image statistics (also see Benjamin et al (2019); Henderson and Serences (2021)) but is also partially due to factors inherent in network architecture. We then leverage results from the study of linear networks to mathematically describe how gradient descent naturally causes learned representations to reflect the input statistics.…”

Section: Introductionmentioning

confidence: 85%

See 1 more Smart Citation

Efficient neural codes naturally emerge through gradient descent learning

Benjamin

Zhang

Qiu

et al. 2022

Preprint

View full text Add to dashboard Cite

Animal sensory systems are more sensitive to common features in the environment than uncommon features. For example, small deviations from the more frequently encountered horizontal orientations can be more easily detected than small deviations from the less frequent diagonal ones. Here we find that artificial neural networks trained to recognize objects also have patterns of sensitivity that match the statistics of features in images. To interpret these findings, we show mathematically that learning with gradient descent in deep neural networks preferentially creates representations that are more sensitive to common features, a hallmark of efficient coding. This result suggests that efficient coding naturally emerges from gradient-like learning on natural stimuli.

show abstract

Section: Resultssupporting

confidence: 92%

Section: Introductionmentioning

confidence: 85%

Efficient neural codes naturally emerge through gradient descent learning

Benjamin

Zhang

Qiu

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…1). First, reproducing and extending previous results (see 29,30 ), we show that deep artificial networks trained on natural image classification show similar patterns of sensitivity as humans. Then, to understand this effect, we mathematically describe how gradient descent causes learned representations to reflect the input statistics in linear systems.…”

supporting

confidence: 88%

Efficient neural codes naturally emerge through gradient descent learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

Human sensory systems are more sensitive to common features in the environment than uncommon features. For example, small deviations from the more frequently encountered horizontal orientations can be more easily detected than small deviations from the less frequent diagonal ones. Here we find that artificial neural networks trained to recognize objects also have patterns of sensitivity that match the statistics of features in images. To interpret these findings, we show mathematically that learning with gradient descent in neural networks preferentially creates representations that are more sensitive to common features, a hallmark of efficient coding. This effect occurs in systems with otherwise unconstrained coding resources, and additionally when learning towards both supervised and unsupervised objectives. This result demonstrates that efficient codes can naturally emerge from gradient-like learning.

show abstract

“…Based on the implications of this theory, i.e., that "consciousness arises from specific types of information-processing computations, which are physically realized by the hardware of the brain" (Dehaene et al, 2017), Dehaene argues that a machine endowed with these processing abilities "would behave as though it were conscious; for instance, it would know that it is seeing something, would express confidence in it, would report it to others, could suffer hallucinations when its monitoring mechanisms break down, and may even experience the same perceptual illusions as humans" (Dehaene et al, 2017). Indeed, it has been demonstrated recently that artificial neural networks trained on image processing can be subject to the same visual illusions as humans (Gomez-Villa et al, 2018;Watanabe et al, 2018;Benjamin et al, 2019) 3.4. Damasio's Model of Consciousness Damasio's model of consciousness was initially published in his popular science book "The feeling of what happens" (Damasio, 1999).…”

Section: The Global Workpace Theorymentioning

confidence: 99%

Will We Ever Have Conscious Machines?

Krauß

Maier

2020

Front. Comput. Neurosci.

View full text Add to dashboard Cite

The question of whether artificial beings or machines could become self-aware or conscious has been a philosophical question for centuries. The main problem is that self-awareness cannot be observed from an outside perspective and the distinction of being really self-aware or merely a clever imitation cannot be answered without access to knowledge about the mechanism's inner workings. We investigate common machine learning approaches with respect to their potential ability to become self-aware. We realize that many important algorithmic steps toward machines with a core consciousness have already been taken.

show abstract

Shared visual illusions between humans and artificial neural networks

Cited by 21 publications

References 0 publications

Efficient neural codes naturally emerge through gradient descent learning

Efficient neural codes naturally emerge through gradient descent learning

Efficient neural codes naturally emerge through gradient descent learning

Will We Ever Have Conscious Machines?

Contact Info

Product

Resources

About