Hierarchical Temporal Memory With Attentional Feedback

Student: Nugamanov Eduard

Supervisor: Aleksandr I. Panov

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2019

Nowadays our knowledge of the brain is actively getting wider. Hierarchical Temporal Memory is the technology that arose due to new discoveries in neurobiology, such as research on neocortex’ structure. One of the most popular applications of this technology is image recognition, because images are close in terms of structure to information which is kept in the brain. Nevertheless both in a real neocortex and in hierarchical temporal memory an image is recognised by its parts. Therefore, there is a problem of choice the most meaningful parts of an image in order to perform fast and effective recognition. In this work we propose the architecture that unites Hierarchical Temporal Memory and Reinforcement Learning. This architecture is perspectively capable of finding an optimal way of the image exploration and effectively classifying them. Besides, we demonstrate the positive effect of such union.

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