Mariusz Pietrołaj - Publikacje - MOST Wiedzy

Wyszukiwarka

Filtry

wszystkich: 7

  • Kategoria
  • Rok
  • Opcje

wyczyść Filtry wybranego katalogu niedostępne

Katalog Publikacji

Rok 2024
  • Limitation of Floating-Point Precision for Resource Constrained Neural Network Training
    Publikacja

    - Rok 2024

    Insufficient availability of computational power and runtime memory is a major concern when it comes to experiments in the field of artificial intelligence. One of the promising solutions for this problem is an optimization of internal neural network’s calculations and its parameters’ representation. This work focuses on the mentioned issue by the application of neural network training with limited precision. Based on this research,...

    Pełny tekst do pobrania w portalu

  • Resource constrained neural network training
    Publikacja

    Modern applications of neural-network-based AI solutions tend to move from datacenter backends to low-power edge devices. Environmental, computational, and power constraints are inevitable consequences of such a shift. Limiting the bit count of neural network parameters proved to be a valid technique for speeding up and increasing efficiency of the inference process. Hence, it is understandable that a similar approach is gaining...

    Pełny tekst do pobrania w portalu

Rok 2022
Rok 2021
  • IFE: NN-aided Instantaneous Pitch Estimation
    Publikacja

    Pitch estimation is still an open issue in contemporary signal processing research. Nowadays, growing momentum of machine learning techniques application in the data-driven society allows for tackling this problem from a new perspective. This work leverages such an opportunity to propose a refined Instantaneous Frequency and power based pitch Estimator method called IFE. It incorporates deep neural network based pitch estimation...

    Pełny tekst do pobrania w portalu

Rok 2020
Rok 2019

wyświetlono 1095 razy