Continuous Online Sequence Learning with an Unsupervised Neural Network Model

Created: 2021-01-31T13:51:17-06:00

Return to the Index
This card pertains to a resource available on the internet.

Reiteration of HTM theory.

Robustness to signal noise, sparseness.

Temporal memory is not robust to temporal noise.

HTM applied to grammar learning was 98.4% accurate while LSTMs were 100%

I don't consider being ~2% less than LSTM to be a considerable flaw given the system is able to learn in real time and LSTMs are not.