Hierarchical Temporal Memory with Reinforcement Learning
Eduard Nugamanov, Aleksandr I. Panov · Procedia Computer Science · 2020
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 the structure of the neocortex. One of the most popular applications of this technology is image recognition and anomaly detection. Nevertheless, both in the neocortex and in hierarchical temporal memory an image is recognized by its parts. Therefore, there is a problem of choosing 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 in order to find the optimal way of image exploration. Besides, we prove by experiments that this architecture is effective, and the quality of the resulting movement pattern is high.