|
|
Neural Network for Autocomplete in the Browser
Kubík, Ján Jakub ; Zemčík, Pavel (referee) ; Kolář, Martin (advisor)
The goal of this thesis is to create and train a neural network and use it in a web browser for English text sequence prediction during writing of text by the user. The intention is to simplify the writing of frequent phrases. The problem is solved by employing a recurrent neural network that is able to predict output text based on the text input. Trained neural network is then used in a Google Chrome extension. By normalized ouput of the neural network, text choosing by sampling decoding algorithm and connecting, the extension is able to generate English word sequences, which are shown to the user as suggested text. The neural network is optimized by selecting the right loss function, and a suitable number of recurrent layers, neurons in the layers, and training epochs. The thesis contributes to enhancing the everyday user experience of writing on the Internet by using a neural network for English word sequence autocomplete in the browser.
|
|
|
Web Browser Extension Providing Protection of Company Data
Dvořák, Jan ; Bednář, Martin (referee) ; Polčák, Libor (advisor)
This thesis focuses on securing company data stored in SaaS storage. In contrast to data stored on-premise, data stored in the cloud face several additional risks, be it from the outside as well as from the inside of the organization. The main risk, whose impacts we try to mitigate in this work, is an accidental data leak by one of the organization's employees. An extension for the Google Chrome web browser was designed and implemented as a solution to this issue. Implementation complications rising from transitioning to a new version of the manifest are also examined in part of this work. The thesis is concluded with the execution of experiments simulating practical data loss scenarios and a verdict on whether a web extension is an appropriate means for creating a tool providing data loss prevention capabilities.
|
|
|
Web Browser Extension Providing Protection of Company Data
Dvořák, Jan ; Bednář, Martin (referee) ; Polčák, Libor (advisor)
This thesis focuses on securing company data stored in SaaS storage. In contrast to data stored on-premise, data stored in the cloud face several additional risks, be it from the outside as well as from the inside of the organization. The main risk, whose impacts we try to mitigate in this work, is an accidental data leak by one of the organization's employees. An extension for the Google Chrome web browser was designed and implemented as a solution to this issue. Implementation complications rising from transitioning to a new version of the manifest are also examined in part of this work. The thesis is concluded with the execution of experiments simulating practical data loss scenarios and a verdict on whether a web extension is an appropriate means for creating a tool providing data loss prevention capabilities.
|
|
|
Neural Network for Autocomplete in the Browser
Kubík, Ján Jakub ; Zemčík, Pavel (referee) ; Kolář, Martin (advisor)
The goal of this thesis is to create and train a neural network and use it in a web browser for English text sequence prediction during writing of text by the user. The intention is to simplify the writing of frequent phrases. The problem is solved by employing a recurrent neural network that is able to predict output text based on the text input. Trained neural network is then used in a Google Chrome extension. By normalized ouput of the neural network, text choosing by sampling decoding algorithm and connecting, the extension is able to generate English word sequences, which are shown to the user as suggested text. The neural network is optimized by selecting the right loss function, and a suitable number of recurrent layers, neurons in the layers, and training epochs. The thesis contributes to enhancing the everyday user experience of writing on the Internet by using a neural network for English word sequence autocomplete in the browser.
|
guest ::
