Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position

By Kunihiko Fukushima. 1980

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

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, background): “Fukushima’s “neocognitron” [19], a biologicallyinspired hierarchical and shift-invariant model for pattern recognition, was an early attempt at just such a process.”
Local Relation Networks for Image Recognition (2019, background): “Convolution Layers and Extensions The convolution layer has existed for several decades [8, 18].”
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (2020, background): “Learning good image representations is a key challenge in computer vision [1, 2, 3] as it allows for efficient training on downstream tasks [4, 5, 6, 7].”
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (2016, neutral): “Convolutional neural networks go back to the 1980s (Fukushima 1980) and (LeCun et al.”
Challenges in representation learning: A report on three machine learning contests (2013, methodology): “The top three teams all used convolutional neural networks [14] trained discriminatively with image transformations.”
Early Convolutions Help Transformers See Better (2021, methodology): “The breakthrough performance of the AlexNet [23] CNN [15, 24] on ImageNet classification [10] transformed the field of recognition, leading to the development of higher performing architectures, e.”
Context Encoders: Feature Learning by Inpainting (2016, background): “Recently, Convolutional Neural Networks (CNNs) [13, 27] have greatly advanced the performance in these tasks [15, 26,28].”
Deformable part models are convolutional neural networks (2014, background): “Convolutional neural networks (CNNs) [12, 23, 27] are another inﬂuential class of models for visual recognition.”
Simultaneous Detection and Segmentation (2014, background): “CNNs have their roots in the Neocogni-tron proposed by Fukushima [15].”
Perceiver: General Perception with Iterative Attention (2021, background): “ConvNets (Fukushima, 1980; LeCun et al., 1998; Cires¸an et al., 2011; Krizhevsky et al., 2012) have been the dominant family of architectures for perceptual tasks for nearly a full decade, thanks to their good performance and scalability.”
End-to-End Training of Deep Visuomotor Policies (2015, background): “CNNs have a long history in computer vision and deep learning (Fukushima, 1980; LeCun et al., 1989; Schmidhuber, 2015), and have recently gained prominence due to excellent results on a number of vision benchmarks (Ciresan et al.”
Representation Learning: A Review and New Perspectives (2012, background): “…(alternating selective feature extraction and invariance-creating pooling) has been the basis of convolutional networks, the Neocognitron (Fukushima, 1980) and HMAX (Riesenhuber and Poggio, 1999) models, and argued to be the architecture used by mammalian brains for object recognition…”
Learning Transferable Architectures for Scalable Image Recognition (2017, background): “The seminal work of [22] on using convolutional architectures [9, 23] for ImageNet classiﬁ-cation represents one of the most important breakthroughs in deep learning.”
Dueling Network Architectures for Deep Reinforcement Learning (2015, background): “Rectiﬁer non-linearities (Fukushima, 1980) are inserted between all adjacent layers.”