Neocognitron: A hierarchical neural network capable of visual pattern recognition

By Kunihiko Fukushima. 1988

Subfields: Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

Scalable Adaptive Computation for Iterative Generation (2022, background): “Influenced by modern accelerator hardware, predominant architectures, such as convolutional neural networks (Fukushima, 1988; LeCun et al., 1989; He et al., 2016) and Transformers (Vaswani et al.”
Deep Reinforcement Learning with Double Q-Learning (2015, background): “Brieﬂy, the network architecture is a convolutional neural network (Fukushima, 1988; LeCun et al., 1998) with 3 convolution layers and a fully-connected hidden layer (approximately 1.5M parameters in total).”
A Survey on Machine Learning Techniques for Cyber Security in the Last Decade (2020, background): “Convolutional neural network (CNN) is a multi-layer neural work that is an extension of feed-forward ANN [238].”
Extracting Slow Subspaces from Natural Videos Leads to Complex Cells (2001, background): “But real world problems like recognition tasks do not only require the network to be specific to the relevant stimulus dimensions but also to be insensitive to the irrelevant dimensions (e.g. Fukushima 1988).”
Image processing with neural networks - a review (2002, methodology): “Others have developed approaches that are invariant to both translation and 2D rotation [144,178], or systems that through their architectures perform processing in a translation-invariant way and=or at diierent scales (e.g., the Neocognitron [150] and the shared weight networks [158,159]).”
Pruning and Quantization for Deep Neural Network Acceleration: A Survey (2021, background): “Pooling was first published in the 1980s with neocognitron [66].”
Deep Learning With Spiking Neurons: Opportunities and Challenges (2018, background): “Models of cortical hierarchies from neuroscience have strongly inspired the architectural principles behind DNNs (Fukushima, 1988; Riesenhuber and Poggio, 1999), but at the implementation level, only marginal similarities between brain-like computation and analog neural networks (ANNs) as used in…”
Artificial intelligence to deep learning: machine intelligence approach for drug discovery (2021, background): “He also developed the first convolutional neural network (CNN) which was based on the visual cortex organization found in animals [25] [Fig.”
Learning a Hierarchical Latent-Variable Model of 3D Shapes (2017, background): “However, ever since the ImageNet contest of 2012 [24], deep convolutional networks (ConvNets) [11, 25] have swept the vision industry, becoming nearly ubiquitous in countless applications.”