Improving Performance of Recurrent Neural Networks

Student: Ignatovskaya Valeriya

Supervisor: Ilya Schurov

Educational Programme: Mathematics (Bachelor)

Year of Graduation: 2018

The paper deals with the problem of exploding and vanishing gradients during the training of recurrent neural networks. Several existing approaches to solution of this problem are described. In particular, unitary recurrent neural networks and ways to implement them are thoroughly explored. In addition, own idea of implementing a unitary recurrent neural network is being developed. The effectiveness of each method of implementation is experimentally demonstrated on topical problems from different areas.

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