HTM Simulation Results (IMAGE) Krause Taylor Associates Caption Numenta used HTM and other algorithms to predict taxi passenger count in the New York City. Left: Overall prediction error for various algorithms. Right: After a new pattern is introduced (black dashed line), HTM quickly learns the new pattern and gives better prediction accuracy than LSTM due to its ability of continuous learning. Credit Numenta, Inc. Usage Restrictions Published under a Creative Commons Attribution 3.0 Unported (CC BY 3.0) license. https://creativecommons.org/licenses/by/3.0/us/ License Licensed content Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.