htm.core
htm.core copied to clipboard
Actively developed Hierarchical Temporal Memory (HTM) community fork (continuation) of NuPIC. Implementation for C++ and Python
SP behaves differently when constructor vs setters are used to set the same parameters! different behavior for constructor vs setters fix for different - [ ] fix test configs https://github.com/htm-community/nupic.cpp/pull/5#issuecomment-417285732...
WIP dropout implementation - [x] dropout works - [ ] move to connections? - [ ] use for SP, TM - [ ] doc EDIT: Motivation: I believe this change...
- [x] removes `Connections.destroyMinPermSynapses()` as not being biologically plausible - replaced by already existing functionality of decaying synaptic weights for un/mis-used synapses and removing "dead" synapses (too low permanence) -...
- [x] conda env for dependencies - [ ] update readme - [ ] cmake aware of conda-installed packages - [ ] packages missing in conda: libyaml, cpp-httplib, mnist-cpp Fixes...
Also see issue #94 Scores 93% on MNIST dataset. Almost nothing else works. Task List: - [x] Merge new MNIST test runner from master - [x] Distal Dendrites via Temporal...
Cleanup boosting in SP. move it into more compact methods, we now have only these: - boostOverlaps_() - (inhibition) - bumpUpWeakColumns_() Where these methods are now more stand-alone. - this...
we used to return likelihood (of the score), but for anomaly we must return `1 - likelihood` Fixes #665 TODO: - [ ] optionally integrate sine wave tests for anomaly...
I am currently working on a small sample project to demonstrate how the REST API can be consumed in C#. However, there are two things I have come across that...
TypeError: Unable to convert function return value to a Python type! The signature was (self: htm.bindings.encoders.RDSE, arg0: float) -> htm::SparseDistributedRepresentation. I am running anaconda 3.7 ( I complied from sources...