HLC 2020 12 01 Prediction of novelty

Pardon me for asking, but my understanding is that HTM models a proposed brain mechanism whereby a sensory input in some encoding is converted into a representation in some standard form (SDR). Then a set or sequence of SDRs is either learned de novo, or is recognised as the prefix of a known sequence and used to predict the next. If prediction is correct the sequence should be reinforced, if not the novel sequence is learned.

I don’t see how concepts such as ‘number’ or ‘bolded’.could exist as sensory encodings. Surely they would have to be SDRs that were generated by algorithms operating on other SDRs? And if I’m not mistaken, those algorithms are currently unknown?

I am a beginner here, my understanding is that the SDR can represent a collection of features. The system can then do object recognition based on the features. In unsupervised learning if will identify features based on the encoding. So if numbers and letters had specific encodings it could learn that feature. Another (more realistic) way to do this is use supervised learning and teach the HTM how to classify the SDR - so it learns a labelled category like number vs letter. A feature like bolded could be learnt for the category of letters. It is not clear to me how that learning would allow for the recognition of a “bold number” in that case.

I would encourage you to expand your view of the scope of SDRs in regards to what and how they encode things.
The examples that are usually shown in HTM are toys - one cell and a dozen or so dendrites. The focus is the mechanics of SDR formation and is on small easily grasped models. With a handful of cells, we see toy models like hot gym or navigation monitoring.

The brain is bigger. Much bigger.

At any given time there are millions of cells working with dozens of SDRs each. Depending on where the cells are in a map in the hierarchy the cells are participating in either the thousand brain voting or forming Calvin tile coding. All at the same time.

The possible symbol-coding space is staggering.

As far as higher-level concepts, if not the cortex in SDRs - then where would these concepts be represented?

The brain is immensely complicated and working out how collections of shapes that we come to know as named letters and relative thickness of these letter shapes combine with general spatial learning to build the concept of “bold,” there are a lot of moving parts to consider. But we know that we do it so it is really a matter of working out how we do it with cortical columns…

It is not too much of a stretch to see how sensory streams register in the sensory cortex to form SDRs. It is even fairly easy to see how the streams up the hierarchy could be parsed in some way to form object recognition and spatial relationships. It takes a little more work to realize that the subcortical structures also project animal sensibilities to the cortex to be processed like external sensations. These sensations include all the animal things like fear, desire, social cues, hunger, thirst, inquisitiveness, exhaustion, and the initiative to initiate actions. This last bit is the key to starting motor actions in the cortex.

The collection of objects, spatial relationships, and the very intimate relation to our personal relationship to our own bodies are all collected in the temporal region, to be acted in the loop of consciousness.

This is the clearest exposition I have ever seen to show how we fit external sensations into our bodies to form higher level semantic constructs and concepts, it’s even short and to the point:
How neurons make meaning: brain mechanisms for embodied and abstract-symbolic semantics - Friedemann Pulvermüller

Much of my posting on this forum have been to expose various aspects of this larger picture. I don’t feel like repeating them all here but if you are interested I can point you to relevant portions.

1 Like

I don’t think people are assuming this in HLC. We have a document showing implementations by participants, for example Etaler with 32x256=8192 cells

Certainly the brain is much bigger, there are certainly functions that require many mini-columns/macro-columns/regions. In this particular thread the discussion is not how to realize an AGI. I’d like to limit the question to whether HTM can predict previously unseen patterns, if it is configured in a certain way.

The example of classifying bolded characters is not to imply the HTM has a concept of bolded characters like a human. It is meant to be a “toy” example to see how/if a relatively simple HTM could learn a category and then use that category to classify previously unseen input. This does not need to imply abstract-symbolic semantics (we provide that by defining the labels).

I would like to try and discuss these in the context of small HTM so we could in theory test the ideas. Small could be considered something that could run on a single computer in a matter of minutes.

It can be fun to imagine what a few million mini-columns might do, but there is little practical use right now unless you have access to the hardware to run tests at that scale.

1 Like

Agreed, so the best starting point is to frame the questions correctly to fit the known properties of the hardware.

Starting with fuzzy thinking about the basic premises of how the hardware works is unlikely to lead to satisfactory answers.

The question was raised about the novelty of seeing a bolded character and I can see how to fit that into the overall structure of representation. Once you do that you can see that seeing a symbol that is somehow different than the learned set of shape would register as novel and trigger learning. At that level in the hierarchy where shape recognition occurs variation from learned shape will be the right level of representation.

Understanding that there are these levels helps to place where the novelty is registered.

The larger concept is that novelty can occur at any level of representation.

The history of AI would tend to indicate otherwise. Many useful things have come from ideas that are not directly bio-inspired. Consider Numenta’s latest work on speeding up deep learning. While these are obviously not going to directly lead to AGI they may be stepping stones.

Even things like making the HTM algorithm more efficient seem very reasonable and certainly are not bio-inspired. HTM is very far from a biological system.

To tie this back to the biology in my “fuzzy” way, as I understand it, there are feedback loops in the neocortex. These are typically not modelled in HTM that are used for object classification or anomaly detection. I suspect that feedback is essential to more general learning - like predicting as yet unseen input. That is where I hope this thread might head.

I agree, and will add that this is so far beyond current state-of-the-art hardware as to be untestable at this time. modeling capability will have to expand by about 3 orders of magnitude to make this possible.

This is not correct, I think 3 people in HLC have run experiments with feedback loops. Martin’s project report provides some details of how that was done with current hardware.

Again, you have to put the novelty in the right place and the answer falls out automatically. The concept of bold is a spatial concept.

We are very good at combining concepts and terrible at thinking of them conceptum novæ.
I have commented on this before:

To phrase it more carefully: there are some very large projects that combine many maps and connections between them.

These have run times in the order of thousands of hours of CPU time and are beyond the reach of most experimenters in the field. I do not have ready access to the technology to experiment with these concepts is any meaningful way. The people that I know that do similar experiments are not able to build these large models and experiment with the model properties to learn how they work.

See:

That said, even with these massive resources the model is at the level of a single event of a single ball passing behind a post.

Where do I get 3 orders of magnitude? to be something I can do as a private experimenter I need to get from thousands of hours of CPU time to tens of hours for any practical experiments.

I am not claiming that it is not a spatial concept. I am not telling you that you are wrong about humans not being able to imagine unseen things. In this thread it would be interesting to explore the idea of how an HTM could predict unseen things (probably through feedback of earlier learning).

I have read extensively about mental imagery.

I can assert with some confidence that this mental manipulation is the combined effort of many systems in the brain and are the result of activation of internal representations that already exist. For the explanation to make any sense you will have to do a lot of learning in how the brain represents spatial concepts.

I can point you to the reading if you are truly interested in getting a through understanding of the concepts. I should warn you that this is likely to take weeks, if not months, to master this material. There is no formal course work on this so you have to pick the concepts out of many only tangentially related texts.

For a very superficial survey of the field:

And an odd, but telling condition that is strongly related to the question at hand:

This thread is not about mental imagery. It is about the HTM algorithm and how it might be modified. By “unseen” I mean the exact same input has not been learnt.

Regarding the concepts of mental representation etc, these are building on very shaky psychological and philosophical foundations. If you want to discuss, we could do that elsewhere, here I’d rather try and keep this thread on the subject of the HTM algorithm.

I really do think you have to be more careful about use of words. What is a ‘collection of featues’? What is the ‘system’? What does it mean to ‘do object recognition’? All we have to work with is SDRs that represent sensory inputs or sequences of other SDRs. You can’t leap from there to objects and features unless you have algorithms to show how.

Getting rather picky here,

  1. SDRs do not encode, they represent (it’s in the name)
  2. Size and architecture don’t matter, algorithms do.

The key computational unit is at the column/micro-column level, size just means you got more of them.

Using words like dendrite and synapse is not helpful. We’re writing code to execute algorithms and we really don’t care how the brain does it biologically.

Introspection is not helpful, we’re stuck at the really low level of algorithms to derive SDRs from other SDRs. We need those small models to find and test those core basic algorithms. Whatever they do is done with an amount of computation easily achievable on desktop computers. IMHO.

What the SDR represent depends on how the program (the HTM system) has been trained. To get labeled categories out of HTM it is trained on labelled data or the output of the HTM is classified by another algorithm.

The HTM algorithm learns spatial and temporal patterns. Similar patterns generate similar SDR and those similarities could be thought of (by the human operator) as features of the inputs.

When relating a set of features with a label this can be considered object recognition. For example, feed a sequence of digits and the feed the output to an SVM decoder that classified the HTM output as a digit.

The HTM algorithm can also be trained to classify, then a simpler decoder can turn the classification represented by an SDR into a label that represents an object.

Regarding introspection (in your next post) check out the video with Hawkins talking about introspection at the beginning.

Thank you, those words are far more carefully chosen.

The video is a tough watch. There is a brief mention of introspection (he likes it, others don’t) with some examples, but they’re stated ‘as fact’. I don’t see that ‘grid cells remapping = sense of being in a different room’ is any different from any other data and hypothesis: how do we measure it? How do we test it?

I was also troubled by the mixing of introspection, theoretical ideas and terms, with some neuroanatomy thrown in.

I tried to follow it, but the sound quality is poor and it skips steps. This is a chat between members of a team, not easy to follow if you’re not already on the team.

Thanks.

I am sorry that the sound quality was poor. That was not obvious during the meeting and I don’t know if any of us listen to the video before it is posted.

As I stated, introspection is just one tool for gaining insights and constraints. I have found it useful in all of our work. I don’t usually call it out but it is there. Other scientists use introspection too, even people who reject it! For example, when vision scientists talk about the stability of visual perception, that we are not aware of our saccades, that is based on introspection. The fact that our perception is stable during saccades tells us that there are some neurons whose firing is stable and other neurons whose firing is changing. The activity of neurons getting input from the retina must change with each new fixation. But there must be neurons whose activity is not changing, these represent your stable perception.

We can take this a step further. If cortical columns implement a common function, then we can deduce that the “changing pattern in some cells” being converted to the “stable pattern in other cells” must occur in each cortical column. This is the fundamental idea behind “pooling” or in our parlance “temporal pooling”. There are many examples like this. Again, introspection usually can’t tell you everything, but it can tell you a lot.

2 Likes

Hi Jeff. I guess I should have realised you would be watching…maybe I should have been more tactful.

Just to make my position clear: I think HTM and the theories immediately surrounding it are a brilliant step forward on a long journey. The idea of an SDR totally changed the way I think about brain(s), memory and sequencing. They feel right (whatever that means).

I distrust the links to neuroanatomy (dendrites and synapses, columns, 6 vs 4 layers) because of the lack of solid science. There are echos that seem plausible, but getting the science right is tough.

If we think about the kind of things going on in brains, there might be (say) 10 or 20 or 50 layers of functional refinement. HTM may give us hints about the 2 or 3 of those layers, introspection gives us a peek at the top 1 or 2. Almost all of our cognitive functioning happens at levels below introspection, and is already complete by the time we become aware of it. I regard introspection as seductive, occasionally useful but highly fallible and often totally wrong. It remains to be seen who is closer to the truth.

I saw a quote from a neuroscientist: ‘Show me, in a maggot’. When we can reliably describe and reproduce the computational behaviour of very simple brains, I will truly believe we are on track. Introspection won’t help with that either.