Приказано за аутора "Denić, Bojan"

Приказ резултата 1-4 од 4

    • Binary Quantization Analysis of Neural Networks Weights on MNIST Dataset 

      Perić, Zoran; Denić, Bojan; Savić, Milan; Vučić, Nikola; Simić, Nikola (Kaunas University of Technology, 2021-08-23)
      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 ...

    • Design and Analysis of Binary Scalar Quantizer of Laplacian Source with Applications 

      Perić, Zoran; Denić, Bojan; Savić, Milan; Despotović, Vladimir (MDPI, 2020-10-27)
      A compression method based on non-uniform binary scalar quantization, designed for the memoryless Laplacian source with zero-mean and unit variance, is analyzed in this paper. Two quantizer design approaches are presented ...

    • Design of a 2-Bit Neural Network Quantizer for Laplacian Source 

      Perić, Zoran; Savić, Milan; Simić, Nikola; Denić, Bojan; Despotović, Vladimir (Molecular Diversity Preservation International, 2021-07-22)
      Achieving real-time inference is one of the major issues in contemporary neural network applications, as complex algorithms are frequently being deployed to mobile devices that have constrained storage and computing power. ...

    • Quantization of Weights of Neural Networks with Negligible Decreasing of Prediction Accuracy 

      Perić, Zoran; Denić, Bojan; Savić, Milan; Dinčić, Milan; Mihajlov, Darko (Kaunas University of Technology, 2021-09-24)
      Quantization and compression of neural network parameters using the uniform scalar quantization is carried out in this paper. The attractiveness of the uniform scalar quantizer is reflected in a low complexity and relatively ...