Results 121 to 130 of about 178,882 (183)

Scaling of Haralick features with image bit depth and gray level co-occurrence matrix displacement vector for linear gradients. [PDF]

Comput Biol Med
Oprisan A, Oprisan SA.
europepmc   +1 more source

EF-Feddr: communication-efficient federated learning with Douglas-Rachford splitting and error feedback. [PDF]

Front Artif Intell
Xue J, Wang C.
europepmc   +1 more source

Scalable and programmable topological transitions in plasmonic Moiré superlattices. [PDF]

Nat Commun
Tian B, Zhang X, Wu R, Zhang Y, Du L, Yuan X.   +5 more
europepmc   +1 more source

Divergence Based Learning Vector Quantization

, 2010
Mwebaze, E., Schneider, P., Schleif, Frank-Michael, Haase, S., Villmann, T., Biehl, M.   +5 more
openaire   +2 more sources

Some of the next articles are maybe not open access.

Related searches:

Soft Learning Vector Quantization

Neural Computation, 2003
Learning vector quantization (LVQ) is a popular class of adaptive nearest prototype classifiers for multiclass classification, but learning algorithms from this family have so far been proposed on heuristic grounds. Here, we take a more principled approach and derive two variants of LVQ using a gaussian mixture ansatz. We propose an objective function
Seo, Sambu, Obermayer, Klaus
openaire   +3 more sources

Divergence-Based Vector Quantization

Neural Computation, 2011
Supervised and unsupervised vector quantization methods for classification and clustering traditionally use dissimilarities, frequently taken as Euclidean distances. In this article, we investigate the applicability of divergences instead, focusing on online learning.
Villmann, Thomas, Haase, Sven
openaire   +3 more sources

Two-stage vector quantization-lattice vector quantization

IEEE Transactions on Information Theory, 1995
Summary: A two-stage vector quantizer is introduced that uses an unstructured first-stage codebook and a second-stage lattice codebook. Joint optimum two-stage encoding is accomplished by exhaustive search of the parent codebook of the two-stage product code.
Pan, Jianping, Fischer, Thomas R.
openaire   +1 more source

Interframe hierarchical vector quantization

International Conference on Acoustics, Speech, and Signal Processing, 1989
An interframe hierarchical vector quantizer (IHVQ) is presented that is capable of encoding image sequence scenes at rates below 0.3 bit per pixel per frame. A regular decomposition quadtree method is used to segment the interframe differential signal into homogeneous regions of different block size.
Nasser M. Nasrabadi, Shihkuan E. Lin, Yushu Feng   +2 more
openaire   +1 more source