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

Neurally-Guided Program Induction

ФИО студента: Denis Rakitin

Руководитель: Kirill Struminsky

Кампус/факультет: Faculty of Computer Science

Программа: Applied Mathematics and Information Science (Bachelor)

Оценка: 10

Год защиты: 2020

The ability of automatically generating a computer program consistent with input and output examples of its evaluation is one of the key properties of the artificial intelligence. Neural program synthesis is an approach for solving this type of problems that allows to use methods of machine learning instead of implementing smart search algorithms and heuristics. One of the main problems with using traditional supervised learning methods here is the necessity of providing a neural network with a large set of programs along with the input-output examples. The main goal of this work is to compare methods that use synthetically generated programs for learning with approaches that do not require ground-truth examples.

Full text (added May 21, 2020)

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