• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Aleksandr Markovich
Sparsification of Gated Recurrent Neural Networks
2019
A lot of tasks in natural language processing (NLP) are successfully solved with recurrent neural networks (RNN) but such models have a huge number of parameters that often leads to an overfitting, slow inference, and impossibility of embedding in devices with limited memory.

The widely used kind of RNN is gated RNN, such as LSTM \cite{LSTM} and GRU \cite{GRU}.

In this study, we will consider structured sparsification of gated RNN based on the pruning of gates and neurons.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses