Thanks for the welcome, David. I guess this isn’t the thread to get into detail, so I’ll limit myself to a few brief comments on your note:
But as I look deeper I realise just how little we know of how the brain really works.
That was surprising to me too - one of my takeaway messages from Jeff’s book.
If the cortical column is the hardware, where is the software? Something must be playing that role.
I’m open-minded on the hardware/software distinction. Should we view synapses as software that “programs” inter-neuron messaging? Or is it more useful to remove the hardware/software distinction and consider everything as continuously evolving “wetware”?
it (not we) will create its successor.
Yes - that hit me like a brick wall when I read Nick Bostrom’s “Superintelligence”.
Looking forward to exploring these and more - thanks again for the kind message meantime.
I’m Matt. I read On Intelligence in 2005 and have been following Numenta since. I’ve been lurking in the forum for the past year, but figured I should post here to introduce myself.
Though nearly all record of it seems to be removed from the Internet, I actually won the 2008 Numenta GAME challenge, back when NuPIC was still new (13 years ago!). It was an excuse to get my copy of the book signed by Jeff Hawkins.
Since then I got my Masters at the MIT Media Lab, worked at a mobile game company, and then co-founded an autonomous drone company.
I’ve also gotten married and had two kids, the most recent of whom has a brain anomaly that is causing development delays. Raising kids has been an incredible experience, and seeing the stark difference between the learning rates in mine has motivated me to really understand more about the human brain at a biological level. I figured that reconnecting with the Numenta community would be a good start.
I look forward to reading more about you all and watching the progress.
I also eagerly await Jeff’s next book…
-Matt
ps: Jeff’s casual dismissal of brain-uploading is one of the most powerful statements I’ve ever heard.
I’m curious for your thoughts on the use of ML or AI to autonomous drones, and if you see any objective there which may be ripe to try some Numenta theory on.
I know some DNNs have gotten good at identifying objects seen by the camera (drawing a box around something and labeling it “person” or “traffic light” or whatever), but beyond that I’m not sure how autonomous it actually gets. I suspect that presenting a new AI-based feature would make a huge splash. Curious what you think.
The Skydio 2 drone has several deep models. They are mostly CNNs that take images and segment people or compute depth, and then those results are combined with hand-written traditional techniques for motion planning. There is a nice overview of the system here
I don’t know enough yet about the latest Numenta theories to try them on drones, but I feel like it would be better to experiment in simulation first rather than trying to do anything real-world practical.
Having something that could predict the best way to fly to a specific location in an un-mapped environment would be interesting. If you aren’t careful, you could enter a cave and run out of battery before you get to your location. There are plenty of traditional geometric search algorithms for this, but I wonder how an intelligent system could leverage cues like walking paths or signs.
I’ll also give the caveat that I’m not an ML expert; I’m just a fan. My background is in systems and games.
I don’t really see a problem here. Falling asleep can be considered a mini death (Jeff also has the same view on that) So why is it so bad If I painlessly black out and wake up, if the simulation is good enough (And I have the opportunity to shut down myself there - fear of infinite torture, [black mirror white Christmas] etc, etc.) The point here really is that one might want to continue experiencing things with the same psychology, memories, emotions (And possibly with close people) that she has now.
Thanks for the link. I must have missed that YouTube, and it’s one of the best overview presentations of the core concepts I’ve seen. Highly recommended.
But that offhand remark is wrong. I’m sure it’s a good conversation starter, but having kids is not the same thing at all. In fact, it’s the only thing. Going back to Kurzweil and before people like to talk about brain cloning or uploading but physics says you can’t. One quantum state wrong, and it’s not a clone…
@scientist1642 I’m not against attempting a brain upload, I’m just no longer susceptible to existential panic about my own death now that I have kids.
Jeff’s statement was intriguing to me before I had kids, and now that I do, I completely agree with him. I doubt brain upload will work any time soon, but maybe raising a digital clone of yourself could happen sooner. If it is feels similar to raising kids, I bet it would offer similar relief to me and perhaps others.
I’d be happy to discuss this at length, but I suspect it would be better in a different forum thread.
I can strongly relate to this, having one child with a development delay and one without, makes me constantly think of the mechanisms that might encompass learning and development (attention, salience, etc).
It has inspired me to focus more learning on the older limbic structures and the role they play.
I’m Alex, and I have just started as a research intern at Numenta. I just graduated from college back in November and am so excited to be working with the fantastic people at this company.
In school I majored in computer science and statistics, but ended up doing a lot of machine learning and neuroscience towards the end. I probably spent more time doing online ML and theoretical neuroscience courses than I spent attending lectures in person. (I’m always open to great online course/YouTube lecture recommendations by the way.)
Last summer, I came across Jeff’s interview on the Lex Fridman podcast and that sent me down a multiple week rabbit hole. I ended up watching just about every public Numenta lecture/research meeting, reading all of the published papers, and also reading On Intelligence. I was pretty astonished that I hadn’t come across this stuff earlier, and that I wouldn’t have seen it but for a stroke of good luck. Numenta’s research seemed to be knocking on the door of fundamental insights necessary for machine intelligence, so I immediately applied to be an intern and here I am!
Besides our shared interest in biologically inspired machine learning/intelligence, I am also fan of Kanye West, the New Orleans Pelicans, poker, brain-machine interfaces, and intellectually stimulating podcasts.
Nice to meet you! I realized that I never actually introduced myself on the forum - I’m Charmaine and I joined Numenta’s marketing team back in August. I’ve been helping @cmaver with the research meeting videos and the promotion of Jeff’s upcoming book so you’ll probably see my name pop up on here from time to time
I came across Numenta in my senior year of college. As a huge tech enthusiast, I’ve learned a lot about the potentials of AI systems and how they can make life so much easier (e.g. Siri, Google Maps). But, as an environmental and economics major, I also learned a lot about the environmental impacts AI can have. I love that Numenta takes a biologically inspired AI approach and to me, it seems like an extremely promising approach towards sustainable AI and AGI.
I look forward to learning all that I can from everyone here and feel free to reach out if you have any questions or feedback on any Numenta events or materials!
My name is Akash, and I joined Numenta as a research intern a few weeks ago. I recently graduated from UC Berkeley studying Electrical Engineering and Computer Science, and spent some time doing robotics and reinforcement learning research.
I got introduced to Numenta through random internet browsings, and through Jeff’s conversation with Lex Fridman on his podcast, and am super excited to be looking at machine intelligence and AI through more of a neuroscience lens as an intern here!
Outside of work/academics, I love pretty watching and playing pretty much all sports and support most LA sports teams. I also enjoy playing the piano and chess.
Looking forward to learning a lot from everyone during my time here!
It’s a pretty remarkable time to be joining Numenta right now- a real sense of tractive foundational knowledge. If I may be so bold to suggest- here are three of my personal favorite articles that denote Numenta’s unique marks in AI research.
The final paper is written by Pentti Kanerva who was with Jeff at Redwood. This is a paper that seems to be easily overlooked in Numenta’s history, but it set out the foundational ideas that underlie SDR. http://rctn.org/vs265/kanerva09-hyperdimensional.pdf
Hi all. I’m an ML engineer for a medical imaging startup. I think deep learning is fundamentally flawed and I’m interested in importing good ideas from outside the field.
Hello everyone,
I am an PhD student, working on applying deep learning for dynamics system modeling.
I first heard about the thousand brains theory on Lex Fridman podcast. Wanting to know more I watched a few videos on youtube (HTM school, a couple presentation) and I am currently reading a the book “A thousand brains”.
I am loving the the concepts described but I am still wrapping my head around a lot of how stuff actually works, mostly when frames of references come in with the “grid cells” and “displacement cells” (how do they work, how do they integrate with TM and SP…). Trying to figuring this out is what brought me here.
Ideally I’d like to explore the “modeling capacity” of HTM given observations of a dynamical system, so if you know of any work that relates I’d be more than grateful
Looking forward to learning more !
I’m Ben, and I’m thrilled to join the HTM community. My academic background is in neuroscience and machine learning. I’ve been interested in the canonical cortical circuit / cortical column for some years, which is how I found out about Numenta. As a researcher here, I’m currently focused on applying principles of 1000 brains theory to machine learning. On the side, I’m also interested in what cortical circuit models can tell us about mental health. I love the enthusiasm and variety of ideas bursting out of the HTM community, and I’m looking forward to learning from and talking with you all.
Hi everyone,
I’m a R&D software engineer with a bachelor’s in physics, living in Boulder, Colorado. For my day job I develop software testing tools, mostly doing full-stack web development using NodeJS, Angular and AWS, with some C++ and Python thrown in.
Neuroscience and the philosophy of mind have been lifelong interests. I recently stumbled on Jeff Hawkins and Numenta while reading a MIT Technology Review article. Other recents: Randall O’Reilly’s Emergent platform and his computational cognitive neuroscience course materials. For contrast, I’ve also taken Andrew Ng’s Machine Learning course on Coursera.
My current focus is the amygdala - locus coeruleus - norepinephrine pathway and its impacts on attention and (ultimately) planning. Yes, this is pretty different from HTM, but so far it looks like these areas are complementary.
I’m blown away by this forum’s “all you can eat” buffet of ideas and the serious open source development occurring on the platform. I’m looking forward to great discussions!
Hi, I read On Intelligence, and added some of the logic to a evolutionary computation framework I wrote years ago (Test framework)
Since that time I have been looking at complex adaptive systems (CAS) developing a framework for helping filter ideas that are supported by CAS logic from any other chaotic ideas. It was a similar logic to Jeff’s view of Mountcastle and his framework for understanding brains. My focus was on the underlying plan: genes, memes, source code; that allow a CAS to evolve.
Thousand Brains fits in really well, since the Cortical Columns can be viewed as agents (Cortical columns)
Not so convinced about Jeff’s logic regarding discarding emotions etc. from future life. Sorry.
I am interested in getting a better understanding of how links work in the cortical column model since if Numenta is right, this will be the way a schematic structure is represented in the brain. I have not found these details yet.
I trained to be a biochemist, which is helpful in looking at CAS, and worked as a programmer for years, then ran some programming projects.
These days I mostly program in Perl, which is powerful, Javascript to activate mouse over on my webpages and c where necessary, and write summaries of books that provide insights about CAS, such as the thousand Brains - see cortical column link.
