TY  - JOUR
AU  - Peric, Zoran H.
AU  - Denic, Bojan D.
AU  - Savic, Milan S.
AU  - Vucic, Nikola J.
AU  - Simic, Nikola B.
PY  - 2021/08/23
Y2  - 2025/01/01
TI  - Binary Quantization Analysis of Neural Networks Weights on MNIST Dataset
JF  - Elektronika ir Elektrotechnika
JA  - ELEKTRON ELEKTROTECH
VL  - 27
IS  - 4
SE  - 
DO  - 10.5755/j02.eie.28881
UR  - https://eejournal.ktu.lt/index.php/elt/article/view/28881
SP  - 55-61
AB  - <p>This paper considers the design of a binary scalar quantizer of Laplacian source and its application in compressed neural networks. The quantizer performance is investigated in a wide dynamic range of data variances, and for that purpose, we derive novel closed-form expressions. Moreover, we propose two selection criteria for the variance range of interest. Binary quantizers are further implemented for compressing neural network weights and its performance is analysed for a simple classification task. Good matching between theory and experiment is observed and a great possibility for implementation is indicated.</p>
ER  -