Coming to this late, but another suggestion @cmaver. Having read On Intelligence and now a regular though infrequent visitor here, it would be great to get ‘level set’. Specifically: what still holds from the first book? What’s been superseded/deprecated, and why? Something to set the right mindset for approaching the new book. Looking forward to it. Thanks for asking.
I’m interested of what speculative ideas Jeff have of connecting the HTM with the rest of the Brain :
1. Long term memory
2. Basal ganglia and/or RL
3. How does HTM algorithm expands to Concept formation
4. What are the parallels between George Lakoff Embodied image schemas and Jeff theory, if any ?
5. Why 150_000 CC seem too few to me to explain what the cortex do ??
/if we grant that a CC can model ~1000 objects/concepts, does capacity 150mln concepts sounds feasible OR if we take account of hierarchy may be 2-3 times as much/
stuff like that. Speculation of beyond-1000-brains theory…
and second, can you please write books more often 
2 Likes
got the book … kewl 
2 min later … whaaat no pictures !! 
Now that I red 2/3 of the book… second part is a slow read.
I hoped to hear more details on the first part of the book… but it seems the book is targeted at the wider public ;(
I don’t care much for the “conciseness” stuff and the AI berserker mode, but I understand that the general public and ivy league professors are obsessed with those and Jeff had to address them. There have to be a contra point to the chicken-little’s .
Technical appendices one level above rookie would have been a good idea …
3 Likes
That reminds me of this old Infocom ad.
(For those too young to remember what tape has to do with computers, Infocom was a company that made text adventure games).
1 Like
I am most interested in part 1. I would like to hear how this frame is being used. I would also love to hear Jeff’s musings on what lies above the cortical column in the brain (if any thing).
2 Likes
Was this a precursor to Mentor Graphics?
I loved the twisty turny maze.
Thank you very much for this opportunity. I received my copy in Germany and as a participant of this forum for over 10 years, I want to pass on my highest compliments to Jeff for this great accomplishment with this book, which recaptures the long path to this great milestone. I fully agree with his assessment that Numenta has now found all the puzzle pieces on the edges, corners and some inner portions of the brains mystery. The framework is now identified. I have two questions I would like to pass on to Jeff:
1.) How is a multi-CC consensus achieved after voting begins? In other words, how is the “invariant” stability reached amongst the voting neurons from each CC? (There is no guarantee they all will always agree, right? They may encounter cognitive dissonance).
2.) Pertaining to learning: If a multiple set of CCs is involved in learning a new object, and each CC is creating an individual model of the same object (i.e. coffee cup), how are all these individually unique models (city maps) in each CC interconnected with each other in such a way, that the same set will be used during inference (perception) so that the voting is based on the same set of models (city maps)? Could this involve some sort of timestamp in episodic memory? (This would allow joint selection during recall). Or is it possible that all the models in the set of CCs are stored in some form of temporal-spatial associative super-structure, encompassing the Thalamus?
I thank you dearly in advance. I want to express my certainty that you have achieved a phenomenal breakthrough, worthy of Dr. Vernon Mountcastle’s admiration.
Your highly motivated follower and community participant,
Joe Anthony Perez
1 Like
I just completed my reading of Part 1. For me this section very definitely falls in the category of “revelation”. It really explains a higher order architecture of the neocortex, that builds upon the HTM paradigm from “On Intelligence”. In fact, if you consider how many paradoxes are plausibly covered and explained by this new TBT framework, it is a true “Aha” moment.
Could anyone inform me about, whether there is already a fixed time and a link or invitation to the event with the Q&A?
In case you haven’t seen it yet, in this thread @cmaver mentioned that they think it makes more sense rather than duplicating a separate Q&A here, to plan on having anyone who is interested in asking questions join the Brains@Bay meeting this coming Wednesday at 10:00 AM PDT. There is a link to Slido for posting questions ahead of time.
If enough folks here want a separate meeting (maybe a lot additional questions we’d like to ask after Brains@Bay, for example), they are open to setting that up as well. Mainly depends on the level of interest.
2 Likes
Thanks, Paul!!
Will the questions posted here be addressed at the Brains@Bay meeting? Or is it expected that we repost them on Slido? (The text limit on slido is very low). It is not easy to phrase a question on such a deep topic, with that limitation.
I have one more question: For me, I see an analogy of the CC maps (object models) in our ability of 10-finger typing skills on a keyboard (especially for us dinosaurs that learned it in school). Each hand has a clear map of a segment of the keyboard. So each hand could represent a CC in our neocortex. (I understand, that the maps in CCs are not adjacent segments of the object, but normally over-lapping with some variance in feature fidelity. So both hands know the keyboard, but some letters are more clear to the left hand and others more clear to the right hand). And we agree that the motor-sensory discovery process (when, for example, exploring an object in order to identify it) requires movement. How do the CCs in the active set of CC (say 1000 CCs) agree on motor-control direction during exploration? Each CC would like to determine which direction to explore next in order to disambiguate. Does some preliminary form of voting already take place during the exploration-disambiguation cycle to agree on, for example, the direction of the next saccade of an eye? Thanks a lot in advance! Joe
PS: BTW, the name I gave myself in this Forum almost a decade ago, was not based on wrong intuition. It sort of fits in to the TBT concept. A Brain-Constellation of CCs was not exactly my vision, but a framework model was in my intuition.
I concur sir
1 Like
Hello! I am collecting all the book related questions posted on this Forum and will be sending them to our Brains@Bay meetup host Lucas. If you’ve already posted a question here or anywhere on the forum, no need to repost them on Slido. You can ask shorter questions there. Hope to see you on Wednesday
2 Likes
Thanks again for this event, I thought it was very exciting. I was mostly interested in technical details, but was surprised to walk away most impressed with Jeff’s answer on racism (and after reading the book, I can see why).