Neocognitron for handwritten digit recognition

By Kunihiko Fukushima. 2003

156 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

High-Performance Neural Networks for Visual Object Classification (2011, methodology): “We tried simple edge masks (Sobel, Scharr) but obtained best results with a contrast-extraction layer (Fukushima, 2003) realized by Mexican hat-shaped ﬁlters of size 21 × 21, one with a concentric on-center receptive ﬁeld and one with a concentric oﬀ-center receptive ﬁeld, Schmid-huber, 1992)…”
Artificial vision by multi-layered neural networks: Neocognitron and its advances (2013, methodology): “In most neocognitrons of old versions, the supervised winner-take-all is used for learning, and the winner-take-all is used for recognition (Fukushima, 2003).”
Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] (2010, methodology): “Similar organizations are utilized by CNNs as well as other deep-layered models (such as the Neocognitron [40] [41] [43] and HMAX [32] [45]), yet more “explicit” cortical models seek a stronger mapping of their architecture to biologically-inspired models.”
Recurrent Processing during Object Recognition (2013, background): “…version of the ventral pathway have explained many aspects of the initial neural response properties across these different brain areas (Fukushima, 1980, 2003; Wal-lis O’Reilly et al. feedforward-driven neural responses theventralpathwayare sufﬁcient tosolvereasonablychallenging…”
On Fast Deep Nets for AGI Vision (2011, background): “We sometimes (but not always) proﬁt from sparse network connectivity and techniques such as weight sharing & convolution [12, 1, 25], max-pooling [17], and contrast enhancement [6] like the one automatically generated by unsupervised Predictability Minimization [18, 22, 24].”