Quantizing of Neural Networks in NLP Domain

Student: Tropin Fedor

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2021

Modern neural networks and machine learning methods have a huge number of parameters. Also, on certain devices, in particular smartphones and tablets, calculations of values in floating-point data types are extremely slow, which leads to the complete uselessness of models that should work in real time. In this paper, we compare the effectiveness of various fake quantization methods. Based on the results of this work, we expect to obtain data on the effectiveness of the applied algorithms on various tasks and at different initial parameters.

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