Use Cases Of HTM Theory

[marty1885]

Yes… I have already done that. You can view a classification problem as a anomaly detection one. And bob’s your uncle.

Learning from real world data (ECG Heartbeat Categorization) as anomaly detection using HTM

If you want to optimise hyperparameters for your task/dataset, I wrote a script to do it here using hyperopt/hyperas: https://github.com/JonnoFTW/htm-models-adelaide/blob/master/engine/vs_model/optimize_htm.py The script should be simple to modify for your use case. You can even do it in a distributed fashion if you have access to many different machines.