An overview of Hierarchical Temporal Memory: A new neocortex algorithm

Abstract

The overview presents the development and application of Hierarchical Temporal Memory (HTM). HTM is a new machine learning method which was proposed by Jeff Hawkins in 2005. It is a biologically inspired cognitive method based on the principle of how human brain works. The method invites hierarchical structure and proposes a memory-prediction framework, thus making it able to predict what will happen in the near future. This overview mainly introduces the developing process of HTM, as well as its principle, characteristics, advantages and applications in vision, image processing and robots movement, some potential applications by using HTM, such as thinking process, are also put forward.