12:10 If there is an example of internal teaching between different brain regions this is a great one. An auditory memory of the goal (his dad’s song), then an exploration of the vocal search space (‘babbling’), then selection of the vocals that have the smallest error compared to his dad’s song. Gr…

Really - how many say they heard a certain style growing up and it inspired them? Very common story.

[image] David Schneider Interview 12:10 If there is an example of internal teaching between different brain regions this is a great one. An auditory memory of the goal (his dad’s song), then an exploration of the vocal search space (‘babbling’), then selection of the vocals that have the smallest…

[image] David Schneider Interview I’d like to develop on the “selection of the vocals that have the smallest error” thing. Depending on how you see that error and selection happening, it may feel as there is still some ANN idea, or a bit from how we think about consciously and actively learning …

[First, a parenthesis about SDR overlap, but that’s not my main question] [image] David Schneider Interview In HTM talk they could be said to have a ‘greater overlap’ when talking about SDRs. I’m quite okay that having a set of possible SDRs makes it possible to chose one with greater overlap…

[image] David Schneider Interview So, I’m not really able either to go from an “error detection” concept in motor development, that I could bring back to the local Hebbian stuff that I expect is really happening. Could you explain that to me ? Sure, Hebbian learning is THE candidate for error-…

Thank you very much for those thoughts. Yes, there must be something of an apically-driven activation at some point, if we want hierarchy to make sense at all. We could even link together “imagination” and “motor” using that. We need to integrate 3 things here in contrast maybe to vanilla TM : t…

[image] David Schneider Interview And we need to wire previous motor to current apical only (or with strong incentive) “in the context where output turned out to be less-kwaky”. (=comparison??). I haven’t really thought about it that far. There are relay connections… possibly using that to pla…

[image] David Schneider Interview This type of experimentation can only be performed on a hierarchy. The ‘H’ is still missing from HTM, so for now we don’t have a model to experiment on. Yes, I know. Although… one of the cell arrays in the current SMI draft could maybe be envisionned as ‘above…

[image] David Schneider Interview Yes, I know. Although… one of the cell arrays in the current SMI draft could maybe be envisionned as ‘above’ the other… even if same area. We could try and extrapolate from that towards a more global view of hierarchies… but granted, we’re not there yet. Sorry…

Thinking through how to actually implement something like this… Through SMI, the motor actions that I am taking will form predictions in the sensory input space. These predictions will then be strengthened/degraded based on the actual sensory input that I hear. This is the area of focus for curre…

Learning how birds teach themselves to sing Dad's song

Engineering

cezar_t December 10, 2021, 4:05pm 18

Ok I cross-link here relevant research How birds learn to sing

Topic		Replies	Views
HLC How to generate behavior with HTM? Community	23	1013	December 18, 2020
Temporal pooler and Receptive fields aka FeedForward Numenta Theory	42	1666	September 17, 2021
Right way to get output from an HTM system Getting Started spatial-pooling	23	1551	August 28, 2021
A different point of view on building AI system Tangential Theories	45	4312	December 2, 2017
Esperanto NLP using HTM and my findings Engineering	59	4593	November 30, 2018

Learning how birds teach themselves to sing Dad's song

Related topics