Hierarchical Temporal Memory (HTM) Whitepaper

Jeff Hawkins • Whitepaper

There have been changes in our thinking, in algorithm implementation, in terminology and in other areas since this paper was written, rendering part of this paper obsolete. Much of this paper has been replaced by BAMI and the current white papers, and we will continue to provide updated material in subsequent releases of BAMI.


At the heart of Hierarchical Temporal Memory (HTM), our machine intelligence technology, are time-based learning algorithms that store and recall spatial and temporal patterns. This paper describes how the learning algorithms work and their biological mapping.

Download Whitepaper

Note: This paper refers to the HTM learning algorithm as the Cortical Learning Algorithm, or CLA; we have recently decided to sunset this term as our technology has evolved.

Translations Available

Language Code Translator Link
Chinese CN Yu Tianxiang Download
French FR Laurent Julliard Download
German DE Ingmar Baetge Download
Japanese JP Akihiro Yoshikawa Download
Korean KR Jihoon Oh Download
Portuguese PT David Ragazzi Download
Russian RU Mikhaile Netov Download
Spanish ES Garikoitz Lerma Usabiaga Download


Jeff Hawkins • Whitepaper