ImageNet classification with deep convolutional neural networks

Krizhevsky, A., Sutskever, & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097-1105.

Type

Journal article

Intellectual base

Primary research

Year

2012

Link

no authoritative link yet

Cited from

cognitive_science, neuroscience

Cited by

2 citations across 2 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Lateral Inhibition
  • Machine learning: Winner-take-all layers and local-response-normalization schemes let strongly activated units suppress nearby units, enforcing sparse, decorrelated representations in which only the most salient features survive.

    This sourceIntroduces local response normalization, in which a strongly activated unit suppresses neighboring units' normalized responses—a lateral-inhibition mechanism enforcing sparse, decorrelated, winner-take-all feature representations.

• Pattern Recognition
  • The tension arises because the two can be conflated: computer vision systems that perform template-matching are sometimes mistaken for perception-like recognition; conversely, human perception is sometimes treated as if it were literal matching.

    This sourceIntroduces local response normalization, in which a strongly activated unit suppresses neighboring units' normalized responses—a lateral-inhibition mechanism enforcing sparse, decorrelated, winner-take-all feature representations.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:52098e5820c0 · see in the full table