Code for: Ferro, D., Gripon, V. and Jiang, X., 2016, July. Nearest neighbour search using binary neural networks. In 2016 International Joint Conference on Neural Networks (IJCNN) (pp. 5106-5112). IEEE.
The code finds nearest neighbours in terms of Euclidean distance, and uses it for classification. The search is optimized by combining Product Quantization (PQ) and binary neural associative memories (Willshaw Neural Networks).
DOI
http://dx.doi.org/10.1109/IJCNN.2016.7727873

Demetrio Ferro e72ac7ac8f Upload files to 'Figures' 1 rok temu
Figures e72ac7ac8f Upload files to 'Figures' 1 rok temu
MNIST b26676a3d3 Upload files to 'MNIST/Neural Networks over PQ' 1 rok temu
TEXMEX f0081e936f Update 'TEXMEX/Data/readme-data.md' 1 rok temu
LICENSE 8ae58179b2 Initial commit 1 rok temu
README.md 161c11ed23 Update 'README.md' 1 rok temu

README.md

Nearest Neighbour Search using binary Neural Networks and Product Quantization

We face the problem of finding nearest neighbours in terms of Euclidean distance, Hamming distance or other distance metric. In order to accelerate the search for the nearest neighbour in large collection datasets, many methods rely on the coarse-fine approach. In this paper we propose to combine Product Quantization (PQ) and binary neural associative memories (Willshaw Neural Networks) to perform the coarse search.

Stored Vectors