Skip to content
Last Dictionary

Kunihiko Fukushima

proper noun

In plain wordsA Japanese engineer who in 1979 invented the neocognitron, a brain-inspired image-recognition network that was the direct ancestor of today's convolutional neural networks.

  1. Japanese computer scientist who spent much of his career at the NHK Science and Technical Research Laboratories, the research arm of Japan's public broadcaster, and later taught at Osaka University and other universities. Inspired by David Hubel and Torsten Wiesel's discovery of simple and complex cells in the visual cortex, he proposed the neocognitronneocognitron, n.: A 1980 neural network for recognizing handwritten characters, modeled on the brain's visual system. Its stacked layers of pattern detectors were the blueprint for the networks used in modern image recognition. (1979; in English 1980), a multilayer network that alternates feature-detecting layers, whose units share weights across positions, with layers that pool their outputs to tolerate shifts and distortions. Trained by unsupervised self-organization, it recognized handwritten characters and is the direct precursor of the convolutional neural networkconvolutional neural network, n.: A kind of neural network built for images and other grid-like data. It slides small pattern detectors across the input, finding edges first, then shapes, then whole objects., which Yann LeCunYann LeCun, prop. n.: A French-American computer scientist who pioneered the neural networks that recognize images, led Meta's AI research for over a decade, and argues that chatbots alone will not reach human-level AI. and colleagues later trained with backpropagationbackpropagation, n.: The method neural networks use to learn from mistakes: it works backward from the error to figure out how much each internal connection contributed, so every connection can be adjusted in the right direction.. His 1969 work on visual feature extraction used the rectifying activation now called ReLUReLU, abbr.: The most common rule a neuron uses to produce its output: keep the number if it is positive, replace it with zero if it is negative. Simple, fast and surprisingly effective.. His honors include the Franklin Institute's Bower Award and Prize for Achievement in Science (2021).

Related

See also
  • neocognitronneocognitron, n.: A 1980 neural network for recognizing handwritten characters, modeled on the brain's visual system. Its stacked layers of pattern detectors were the blueprint for the networks used in modern image recognition.
  • convolutional neural networkconvolutional neural network, n.: A kind of neural network built for images and other grid-like data. It slides small pattern detectors across the input, finding edges first, then shapes, then whole objects.
  • poolingpooling, n.: A step in an image network that shrinks its internal picture by summarizing each small patch with one number, usually the largest or the average, keeping what matters and discarding exact positions.
  • receptive fieldreceptive field, n.: The patch of the original input, such as a region of an image, that a particular neuron inside a network can see and respond to.
  • ReLUReLU, abbr.: The most common rule a neuron uses to produce its output: keep the number if it is positive, replace it with zero if it is negative. Simple, fast and surprisingly effective.
  • Yann LeCunYann LeCun, prop. n.: A French-American computer scientist who pioneered the neural networks that recognize images, led Meta's AI research for over a decade, and argues that chatbots alone will not reach human-level AI.

Sources

  1. Fukushima, K. (1980). Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36(4): 193–202.

Mentioned in

neocognitronneocognitron, n.: A 1980 neural network for recognizing handwritten characters, modeled on the brain's visual system. Its stacked layers of pattern detectors were the blueprint for the networks used in modern image recognition.