Competitive learning and soft competition for vector quantizer design

By E. Yair, Kenneth Zeger, A. Gersho. 1992

How researchers see this paper

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

Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations (2017, methodology): “Formally related but motivated from a probabilistic perspective are deterministic annealing methods for maximum entropy clustering/vector quantization, see, e.g. , [24, 42].”
Soft-to-Hard Vector Quantization for End-to-End Learned Compression of Images and Neural Networks (2017, methodology): “Arguably most related to our approach is (Wohlhart et al., 2013), which also employs continuation for nearest neighbor assignments, but in the context of learning a supervised prototype classifier.”
Deterministic annealing for clustering, compression, classification, regression, and related optimization problems (1998, methodology): “Another approach was to use stochastic gradient techniques [16], particularly in conjunction with self-organizing feature maps, e.g., [22] and [107].”
Clustering: A neural network approach (2010, unknown): “Examples are the SCS (Yair et al., 1992), the SOM (Kohonen, 1989), the NG (Martinetz et al.”
Prototype-based Neural Network Layers: Incorporating Vector Quantization (2018, methodology): “A model is trained either by a heuristically motivated update of the prototypes or by the optimization of a cost function [17, 18, 19].”