Online Labelling Strategies for Growing Neural Gas

17 citations recorded by the source corpus.

How researchers see this paper

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

Lifelong learning of human actions with deep neural network self-organization (2017, background): “Self-organizing networks have shown state-of-the-art results for classification tasks with different techniques proposed to attach symbolic labels to prototype neurons (e.g. Beyer & Cimiano, 2011; Parisi et al., 2015).”
Emergence of multimodal action representations from neural network self-organization (2017, background): “The overall approach is said to be online since the algorithm incrementally propagates labels during the training process (Beyer & Cimiano, 2011), in contrast to offline methods where labels are used after the unsupervised training of a network has finished.”
Self-organizing neural integration of pose-motion features for human action recognition (2015, methodology): “For the classiﬁcation task, we deﬁne a recognition function ψ : → L on the basis of a single-linkage strategy (Beyer and Cimiano, 2011) in which a new sample 9 new is labeled with l j associated to the neuron n that minimizes the distance to the new sample: The hierarchical ﬂow is composed of 3…”
Human Action Recognition with Hierarchical Growing Neural Gas Learning (2014, methodology): “The adopted labelling techniques have shown to achieve best classification accuracy among other offline labelling strategies [14].”