"neural networks" - Selaus asiasanan mukaan Kandidaatintutkielmat

Viitteet 1-5 / 5

    • Content-Driven Automatic Equalization For Audio 

      González Villegas, Julio (2020)
      Kandidaatintyö
      We can find equalizers in most of the modern day music players, and these equalizers usually include presets that the user can select, according to the genre of the song that is going to be played, or create their personal ...

    • Neural networks in household investor behavior prediction 

      Eneh, Lauri (2020)
      Kandidaatintyö
      Machine learning (ML) has been widely applied to various fields and areas, including the financial market. In this study, the behavior of active Finnish household investors is being predicted using three different neural ...

    • Robustness Analysis of High-Confidence Image Perception by Deep Neural Networks 

      Ahonen, Jukka (2020)
      Kandidaatintyö
      Deep neural networks are nowadays state-of-the-art method for many pattern recognition problems. As the performance grows, the robustness of them cannot be ignored. Specifically, the lack of robustness against slightly ...

    • Sequence Temporal Sub-Sampling for Automated Audio Captioning 

      Nguyen, Khoa (2020)
      Kandidaatintyö
      Audio captioning is a novel task in machine learning which involves the generation of textual description for an audio signal. For example, a method for audio captioning must be able to generate descriptions like “two ...

    • Visualization of Semantic Segmentation Networks 

      Kankainen, Ossi (2020)
      Kandidaatintyö
      The development of visualization methods for deep convolutional neural networks supports their design and helps in their adaption also to critical applications. Semantic segmentation has many such heavily regulated application ...