htmresearch
htmresearch copied to clipboard
numenta
Experimental algorithms. Unsupported.
Bumps [numpy](https://github.com/numpy/numpy) from 1.12.1 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 1.12.0 to 2.7.2. Release notes Sourced from tensorflow's releases. TensorFlow 2.7.2 Release 2.7.2 This releases introduces several vulnerability fixes: Fixes a code injection in saved_model_cli (CVE-2022-29216) Fixes...
@subutai Similar to your proposal of running the noise tests once only on the best trained model instead of all models during training
@subutai Please review. The main change in this PR is the switch from `BatchNorm` to `LayerNorm` on `LinearSDR` module. See https://arxiv.org/abs/1607.06450
https://github.com/numenta/htmresearch/blob/6a823ff7fce4401614230d9ec5cf6572759443d6/htmresearch/algorithms/union_temporal_pooler.py#L212 Shouldn't that be `totalOverlap` instead of `overlapsPredictedActive`? Otherwise it will only activate with predictedActive input and apply the weighting only in case of learning. I know this is not...
Relevant code: https://github.com/numenta/nupic.core/blob/8a846d1d897440bc6ca1e46120520da166bc551a/src/nupic/experimental/ExtendedTemporalMemory.cpp#L616 I didn't change the algorithm at all, I just put all the logic for "learning cell" selection in one place. When a column is bursting, we choose...
Moved from https://github.com/numenta/nupic/issues/910. Please see discussion there.
Clone of (now closed) NuPIC issue https://github.com/numenta/nupic/issues/894 As per https://github.com/numenta/nupic/issues/892, might be worth experimenting with the following approach: "Permanence values for shared inputs, which are input bits that are turned...
The simple labels and hello classification tests for sensor_knn.json config fail -- 52.98% vs 66.2%, and 60% vs 80%, respectively. @subutai would you please confirm you get the same?
