• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
For visually-impairedUser profile (HSE staff only)SearchMenu

The Research of the Сatastrophic Forgetting Problem when Training Neural Networks

Student: Vyacheslav Prischepa

Supervisor: Liudmila Zhukova

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2020

Catastrophic forgetting – the main issue which impedes implementation of online learning the neural networks and other models based on gradient methods. There was paid special attention to study of this task and possible solutions. As the practical results of the work occurred own algorithm allowing to prevent the forgetting. Also, there was proved the working capacity of this one in different scenarios of training the deep neural networks, which are not available using the standard approaches of machine learning.

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