Computational optimization of Neural Network Pipelines

Student: EfimenSov Veaceslav

Supervisor: Yuri Baevsky

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Business Informatics (Bachelor)

Year of Graduation: 2019

Over the past five years, there has been a rapid growth in the use of neural networks and machine learning, accompanied by a variety of studies and practices that apply these methods to a wide range of applications, such as: image and video classification, speech recognition, language translation. As neural networks have become more widely developed and used, model sizes have grown, to improve efficiency—models today have tens or even hundreds of layers totaling 10-20 million parameters. This growth not only highlights the already labor-intensive and resource-intensive learning processes of neural networks, but also leads to the emergence of new tools to optimize complex neural networks.

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