Rok 2020

• Benchmarking Deep Neural Network Training Using Multi- and Many-Core Processors

  Publikacja

  • P. Czarnul
  • K. Jabłońska

  - International Journal of Computer Information Systems and Industrial Management Applications - Rok 2020

  In the paper we provide thorough benchmarking of deep neural network (DNN) training on modern multi- and many-core Intel processors in order to assess performance differences for various deep learning as well as parallel computing parameters. We present performance of DNN training for Alexnet, Googlenet, Googlenet_v2 as well as Resnet_50 for various engines used by the deep learning framework, for various batch sizes. Furthermore,...

  Pełny tekst do pobrania w serwisie zewnętrznym

• Collaborative Data Acquisition and Learning Support

  Publikacja

  • T. M. Boiński (dawniej: T. Boiński)
  • J. Szymański

  - International Journal of Computer Information Systems and Industrial Management Applications - Rok 2020

  With the constant development of neural networks, traditional algorithms relying on data structures lose their significance as more and more solutions are using AI rather than traditional algorithms. This in turn requires a lot of correctly annotated and informative data samples. In this paper, we propose a crowdsourcing based approach for data acquisition and tagging with support for Active Learning where the system acts as an...

  Pełny tekst do pobrania w portalu