Cresceptron: a self-organizing neural network which grows adaptively

By Juyang Weng, Narendra Ahuja, Thomas S. Huang. 1992

How researchers see this paper

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

Citations in the corpus

Deep learning in neural networks: An overview (2014, methodology): “4) inspired the Cresceptron (Weng et al., 1992), which adapts its topology during training (Section 5.”
Deep Networks with Internal Selective Attention through Feedback Connections (2014, background): “The usual approach is to take the maximum value among non- or partially-overlapping patches in every map, therefore reducing dimensionality along the height and width [2].”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “As the history grows, to find an M with small bitsM + bitsH , step 4 uses sequential network construction: it regularly changes M ’s size by adding or pruning units and connections [111, 112, 8, 168, 59, 107, 304, 176, 141, 92, 143, 204, 53, 296, 106, 31, 57, 185, 283].”
One Big Net For Everything (2018, background): “If there are large 2-dimensional inputs such as video images, the LSTM may have a front-end [95] in form of a convolutional neural net (CNN) [11, 33, 97, 4, 45, 52, 8, 76] implemented on fast GPUs [8, 76].”
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation (2017, unknown): “small shift invariance through pooling layers [62, 55, 7].”
Stacked Convolutional Denoising Auto-Encoders for Feature Representation (2017, background): “The other property is convolution [16] and pooling [17] structures.”
Deep Learning and Its Applications in Biomedicine (2018, methodology): “ANNs mimicked the perception of objects by connecting artiﬁcial neurons within layers that could extract the features of objects [11–16].”
Learning Recognition and Segmentation Using the Cresceptron (1997, result): “Some partial preliminary results of the work reported here were presented during 1992–1993 at a few conferences (Weng et al., 1992, 1993; Weng, 1993).”
Scalable, High-Quality Object Detection (2014, methodology): “This leads to the construction of a variant of the Inception network, where in parallel to the large pooling layers [30] stride-2 convolutions are used in the Inception modules when reducing the grid size.”