htm.core
htm.core copied to clipboard
Actively developed Hierarchical Temporal Memory (HTM) community fork (continuation) of NuPIC. Implementation for C++ and Python
I'm having trouble performing anomaly detection in python. I'm using the hotgym example and am struggling to detect anomalies. I posted on the htm forum earlier and think this is...
Review of encoders' coverage of sensory modalities https://github.com/htm-community/htm.core/issues/259 Here we look at possibilities of HTM networks: ### Tasks: - [x] prediction - [ ] multi-step ahead prediction: - TODO: instead...
Work In Progress See also issue #258 & #259. Use the following python script to view the Receptive Fields of the simulated place cells: ```Python import numpy as np from...
Hi, I tried installing using the read me, using python -m pip install -i https://test.pypi.org/simple/ htm.core but got the following error: ERROR: Could not find a version that satisfies the...
Currently we're releasing python packages to pypi's test server, not their production server. It would be nice if this project were located on the production server. If it were on...
Hi @dkeeney, I tried making a new release, but I got the following error messages, which prevented the python packages from being built & uploaded to the test server. All...
I think for higher prediction and robuster anomaly detection, we need something like a chain of 10 TMs for 10 steps prediction: TM0->TM1->TM2->...-->TM9, where the predicted cells of the previous...
This is not an issue rather a question, what should be the resolution of RDSE set to for encoding 32bit floats. If you feel that this is not the right...
I have never really liked the SDRClassifier algorithm because it requires a lot of training before it can reliably classify (it uses a classical NN). I have noticed that some...
See comments [https://github.com/htm-community/htm.core/pull/873#discussion_r486977186](https://github.com/htm-community/htm.core/pull/873#discussion_r486977186) Probably needs just create bindings for enum. Now can be bypassed by using save() and saving as binary stream, like: ``` with open(filepath+"_basal.dump", "wb") as f: f.write(self._tm.basalConnections.save())...