HTM and Deep learning

Science Numenta Theory
1

hi, all of us know that HTM is

  • REAL-TIME
  • Continuous learning: the model should learn online as the data comes
  • Unsupervised: no one is going to label the data. NEVER.
  • Not CPU “greedy”
  • No hyper-parameter tuning or other human intervention
  • Noise robustness

but I want to know if HTM is more faster that LSTM in training and prediction ?and in precision of detection anomaly .
If there is any paper or anything

3 Likes