Introduce yourself!

Hi Everyone!
Found this forum after reading On Intelligence. Still have a lot to read here, but already see some very interesting discussions.

My area of expertise is digital hardware design (mostly ASIC). I’ve done coprocessors with fast memory access, using both embedded memory blocks and external RAM. Familiar with CAM (Content Addressable Memory).

There can be a lot of transistors on a chip these days, but the existing computing architecture does not use the full potential of the technology. It is all about number of cores and cache size, but these are evolutionary advances. I feel that HTM can offer a new revolutionary application for the current silicon technology.



Dear all,
I feel that is a long and full of stories journey when I glance over other people’s reply.
I am a new comer to this forum. And now I am a master candidate in computer science in BUPT(China).

Since age 12 or so, after hearing about the Turing Test, the main goal of mine has been to build a general artificial intelligence similar to human beings. My undergraduate laboratory’s machine learning projects rekindle my dream. After worked on several projects I realized it is no possible to build a general artificial intelligence based on traditional machine learning technology. However, I did exercise my programming skills through my undergraduate program. My undergraduate graduation design is reinforcement learning which is described as “the cherry on the cake” by Lecun.

With the rise of deep learning, I dived into artificial intelligence courses and got familiar with machine learning platforms like Tensorflow and Pytorch. Those platforms can help researchers to realize their genius ideas of artificial intelligence. Furthermore, I have co-founded an offline platform for learning more knowledge from other researchers. Although read lots of papers and articles, I did not find out any clues. Whether Hinton’s capsule network or Lecun’s self-supervised learning or Jurgen Schmidhuber’s world model or Bengio’s consciousness prior, their theories can’t give a clear answer of how to achieve general artificial intelligence. Because nowadays the so-called artificial intelligence usually focuses on specific tasks and limited by neuroscience’s understanding of internal working mechanism of brain.

With the dream of AGI(Artificial General Intelligence) , I finally found here.


I guess I’m the latest arrival to this excellent website. I ‘found’ it via a New York Times article and it’s been the most depressing and exhilarating hour of browsing since. Exhilarating because you guys at Numenta are in an exclusive group who are almost certainly getting it right (!); and profoundly depressing because I’ll never catch up!

A bit of personal background.

I’m a chemist by background (Oxford 1975 – 79) but I gave up being a proper chemist in 1979 and have been in the finance/venture capital world for nearly 40 years now. However, for the last 9, maybe 10, years I’ve been marginally obsessed by how real brains think in the sense of processing sensory information and then acting. The ‘obsession’ actually goes back further; it started at about 6am on a wet November morning in 1976 when I had to get up out of a warm bred to prepare punched cards for a Fortran program which calculated frequencies for the vibrational modes for CO2; my over-riding thought at the time was that there had to be some better way to model systems than punched cards on a digital computer. It’s what a cold, wet November morning does to a young undergraduate I suppose, especially as he’s leaving the girlfriend de jour behind in the bed.

At the time I put a bit of preliminary thought into non-binary logic and an oscillatory wave approach to information processing and got absolutely nowhere; I’d done a bit of quantum theory but the maths requirements, especially Fourier manipulations, were too difficult. After university, I gave very little thought to alternative logic systems and over the next 30 years raised a family and got on with a career. Then in 2008 there was quite a bit of speculation in the popular science magazines about next generation AI and I started, in a clumsy way, thinking about thought processes again.

I’m still not sure I’ve got anywhere! But back in 2009 I did a calculation of the sort that only chemists do which was estimating the atomic weight of the average neuron from which I deducted the very approximate contribution from water and lipids and so got to an estimated number of very big complex protein molecules - possibly as much as 200,000 per cell as an average over all neurone and glial cells. It begged the question of what (as in WTF) were they all doing because the electrochemical switching duties of a well-connected pyramidal cell are probably quite significant and the big proteins surely have to be involved. Further, the chemical environment such a cell lives in might include several 10’s of types of neurotransmitter delivered to it at various times and under varying circumstances. Definitely not digital then.

Then in 2012 I read Professor Dennis Bray’s excellent book ‘Wetware’ and realised that the concept of the brain cell (of whatever type) having quite a sophisticated, internal information processing role was beyond doubt. Obvious really because, after all, amoebas can ‘learn’ in a basic way.

Where I’ve got to in my amateurish way is that a brain is essentially a complex community of specialist amoeba-like cells.Their interactions once in place in the matrix are incredibly subtle and the net result is possibly not even a Turing machine…? I tentatively think they assemble into a co-operative matrix through a series of iterative trial-and-error cycles and fundamental to this is the feedback processes which eventually result in a Darwinian elimination of the ‘wrong’ links. It’s a long process (years) for the sophisticated brain to evolve in this way but I think it’s the dynamic process underpinning the design of an efficient architecture for decision making by the organism which owns the brain.

Anyway, I’m glad I found you. Please let me know if any of the team are coming to London, or anywhere in the UK, to do a bit of proselyting/lecturing!



My name is Michael and I’m currently studying for an MSc. in the field of Space Engineering in Surrey, England.

As a Thesis topic, I was assigned to investigate the potential of Machine Learning algorithms for real-time anomaly detection in Satellite telemetry data. After a lot of of digging I eventually came across HTM and was pleasantly surprised. There seems to be a lot of research in the Space industry regarding LSTM networks, but barely any regarding HTM networks. I currently have access to Satellite telemetry data so I thought it would be fun to see how an HTM can perform. Eventually, I’d like to form a Concept of Operations for an HTM network working on-board a Satellite on some telemetry channels. This involves quantifying the memory requirements of a high-performing HTM network and a trade-off analysis regarding performance and time resolution,number of input features and number of channels being studied. Obviously there are a number of complex issues regarding the actually implementation, but would appreciate any advice or ideas people may have, especially for reducing the computational requirements of the network.

Due to my limited background in the field, this project was always going to be a stretch for me, but I’ve really enjoyed the stuff I’ve learned so far and am looking forward to pushing the concept as far as I can.

Thanks :))


2 posts were split to a new topic: NuPIC on satellite data

My name is Syed Abdullah Shahbaz.
I graduated in Electronics & Communication. I got excited by Jeff Hawkins keynote. Reading “On Intelligence” right now.Seeing someone reverse engineer the human brain got my 100% attention. It inspired alot of peoples like me who got sick and tired of ML,i was exploring other ways and finally i found my less trodden path.


That is great! We are looking for people looking for real answers. :slight_smile:

1 Like


My name is David Duckworth and I am a full stack developer (20+ years) with most dev lately being in TypeScript/JavaScript and React. I have been following Numenta and Jeff for almost 10 years and have studied neuroscience and AI in general for almost 20 years. Look forward to contributing!


Hi David! Thanks for joining and also thanks for following me on Twitch. :slight_smile:


Hey there @David_Duckworth welcome, glad to have you here.

1 Like

Hello fellow newbies and seasoned veterans,

There may be no better place where one might come to terms with the workings of the mind than the Numenta community forum and to that end hope we might be able to ask some questions without being offended nor offending anyone else.


Hi everyone!

My name’s Jeremy and I’ve recently started learning about the HTM theory after seeing Jeff give a talk at my university. I’m currently a cognitive neuroscience master’s student exploring virtual reality navigation through human intracranial recordings of the hippocampus. My work leans heavily on using ML for feature decoding. I’m excited for the prospect of applying brain-inspired ML to brain data and hope to apply some of the HTM learning algorithms to my intracranial EEG data.

Jeff pointed out during his talk that theory is a major bottleneck in neuroscience which really sparked my interest. I sometimes hang out in Matt’s twitch streams, and hope to become more active in the community.

Thanks :smiley:


Welcome @JSaal! In case you’d like to get specific about your data and objectives we can help you hone NuPIC to them.

Welcome! @JSaal


I’m Lucas. Like everyone here, I read Jeff’s book many years ago, and it was truly inspiring for me - from all the popular neuroscience books I was reading at the time, I just felt that this was the closest to the true answer. I’ve been following Jeff and Numenta ever since.

My background is on data science and machine learning. My latest research was on accelerating deep reinforcement learning in multiagent scenarios through experience sharing. I’m currently a member of the research team at Numenta, focusing on applying HTM principles to address the flaws of traditional machine learning algorithms and push the state of the art.

One of the things I most admire about Numenta is this amazing community, so I feel proud to be a part of it. I’m chronically shy on social media platforms (my last facebook post is from 2015), but I am trying to improve on this, so please forgive me if I don’t contribute much in the forums. I do read a lot of the discussions, which I find extremely interesting and thought provoking. I learned a lot from you and I hope to continue learning in the coming years.

I am very open to collaboration, exchanging ideas and projects, so please feel free to reach me through here, my email (lsouza at numenta dot com) or drop by any time for some coffee. And I hope we can meet soon in one of the community meetups.


Howdy all!
I’m Mark Brown, I have been a Data Engineer working in Santa Barbara CA for the past 10 years. I actually live in Gilbert AZ now though.
I ended up here from an article on doing ML in Snowflake, which sounds awesome and I am excited to check it out.


Hi @lucasosouza, great to meet you at last night’s event, and I’m excited to see some ML applications emerge.

Hi @mark_brown, thanks for reading my medium article and happy to hear it brought you here. I hope you don’t get mistaken for @Bitking too often!


I am Mark Browne - clearly different.
Or Bitking, less to get wrong.

Welcome Mark Brown.


Thanks, yeah there are a lot of Mark Browns out there.
I have the markbrown gmail address and it has had an interesting history of emails I get and take over attempts.


Oh cool, I’m in SB now finishing my degree! Where do you work?