Monday, September 25, 2017

Fast Unsupervised Sequence Learning Using Spike Timing (1)

Novel Memory Architecture

Previously in this series on unsupervised learning, I explained how to implement a fast unsupervised pattern learning network based on spike timing. In this article, I introduce a novel architecture for sequence memory. Its purpose is to emulate the brain's flexible perceptual abilities.

Note: I originally intended this to be a single blog post but the subject is too vast for one post to do it justice. Expect one or more more installments after this one.

The Magic of Sequence Memory

Sequence memory is the seat of knowledge and cognition. This is where most of the magic of perception happens. It is the part of the brain that gives us a common sense, cause-effect understanding of the world in all of its 3-dimensional grandeur. Equally impressive is its ability to make highly accurate guesses when presented with incomplete or noisy sensory information. This ability is the reason that we have no difficulty recognizing highly stylized art or seeing faces and other objects in the clouds. Take a look at the image below. Those of us who are familiar with farm animals will instantly recognize the face of a cow even if we have never seen the picture before. Don't worry. Some of us never see the cow.

Font designers rely on the brain's ability to almost instantly classify objects according to their similarity to other known objects. Without it, we would have a hard time recognizing words written in unfamiliar fonts. It can also be used to play tricks on the brain. Cognitive scientist Douglas Hofstadter and others have written about this. Consider the ambigram below. We can read the bottom word as either 'WAVe' or 'particle'. How is that possible?
This magical flexibility is the gift of sequence memory. The brain can quickly recognize sequences at various levels of abstraction based on very little or even faulty information. My point here is that, unless we can design and build our neural networks to exhibit the same capabilities as the human brain, we will have failed. I am proposing a novel architecture for sequence memory that, I believe, will solve these problems and open up the field of AGI to a glorious future.

Note: Sequence memory is also the source of all voluntary motor signals and is essential to motor learning. I will cover this topic in a future article.

Math Is Not the Answer

At this point, some of you may be wondering why I use no math in my articles on AI. The reason is that the brain does not use it. Why? Only because its neurons are too slow and there is no time for lengthy calculations. Not that I have anything against math, mind you, but if you hear anyone claiming that AGI cannot be achieved without doing some fancy math (which is just about everybody in mainstream AGI research), you can rest assured that he or she hasn't a clue as to what intelligence is really about.

The Brain Assumes a Perfect World

One of the most specious yet ubiquitous myths in mainstream AI research is the notion that the world is uncertain and that, therefore, our intelligent machines should use probabilistic methods to make sense of it. It is a powerful myth that has severely retarded progress in AI research. I am not the first to argue this point. "People are not probability thinkers but cause-effect thinkers." These words were spoken by none other than famed computer scientist Dr. Judea Pearl during a 2012 Cambridge University Press interview. Pearl, an early champion of the Bayesian approach to AI, apparently had a complete change of heart. Unfortunately, the AI community is completely oblivious to any truth that contradicts their paradigm.

As I have said elsewhere, we can forget about computing probabilities because the brain's neurons are not fast enough. There is very little time for computation in the brain. The surprising truth is that the brain is rather lazy and does not compute anything while it is perceiving the world. It assumes that the world is perfectly deterministic and that it performs its own computations. The laws of classical physics and geometry are precise, universal and permanent. Any uncertainty comes from the limitations of our sensors. The brain learns how the world behaves and expects that this behavior is perfect and will not deviate. The perceptual process is comparable to that of a coin sorting machine whereby the machine assumes that the various sizes of the coins automatically determine which slots they belong to.

We cannot hope to solve the AGI problem unless we emulate the brain. But how can the brain capture the perfection that is in the world if it cannot rely on its sensors? It turns out that sensory signals are not always imperfect. Every once in a while, even if for a brief interval, they are indeed perfect. The brain is ready to capture this perfection in both pattern and sequence memories. None of the magic of perception I spoke of earlier would be possible without this capability.

Sequence Memory

Sequence memory is organized hierarchically and receives input signals from pattern memory. These signals arrive at the bottom level of the hierarchy and a few percolate upward to the top level. The number of levels depends on design requirements. I happen to know that the brain's cortical hierarchy has 20 levels. This is much more than is necessary for most purposes in my opinion. It is a sign that we can think at very high levels of abstraction. I estimate that most of our intelligent machines, at least in the beginning, will require less than half that number. In a future article on motor learning and behavior, I will explain how the bottom level of the sequence hierarchy serves as the source of all motor signals.
In the diagram above, we see three sequence detectors A, B and C (red filled circles) on two levels. Sequences A and C on level 1 receive inputs directly from 7 patterns neurons (blue filled circles). Unfinished sequence B on level 2 has only two inputs arriving from sequences A and C. The red lines represent connections to the output nodes (see below) which are the only pathways up the hierarchy.

The sequence is the building block of sequence memory. It is a 7-node segment within a longer series that I call the vine. The 7th node is the output node of the sequence. Every node in a sequence receives signals from either a pattern neuron or another sequence. Vines and sequences receive signals in a specific order separated by an interval. The interesting thing about a sequence is that it does not have a fixed duration. That is to say, the interval between nodes can vary. This is extremely important because, without it, we would not be able to make sense of the 3D geometry of the world or to understand events when their rates of occurrence change over time.
In the early days of my quest to understand the brain and intelligence, I used to think that the sequence hierarchy was just a way to organize various combinations of long sequences. I had assumed that a sequence at the top of the hierarchy was just a container for other shorter sequences at the lower levels. I cannot go, at this time, into how I eventually changed my mind but I was completely wrong. It turns out that the brain builds all of its sequences/vines at the bottom level of the sequence hierarchy. The upper levels are used primarily for finding temporal correlations between sequences and for building special structures called branches which are used for the invariant detection of complex objects in the world.

Coming Soon

In my next article in this series, I will explain how to use spike timing to do fast unsupervised sequence learning. I will explain how sequence detection occurs with relatively few sensory signals. I will also introduce a model for the brain's cortical column based on this architecture. Stay tuned.

Note (11/16/2017): I will eventually publish the next article in this series. Now is not the time.

See Also:

Fast Unsupervised Pattern Learning Using Spike Timing
Unsupervised Machine Learning: What Will Replace Backpropagation?
AI Pioneer Now Says We Need to Start Over. Some of Us Have Been Saying This for Years
In Spite of the Successes, Mainstream AI is Still Stuck in a Rut
Why Deep Learning Is A Hindrance to Progress Toward True AI
The World Is its Own Model or Why Hubert Dreyfus Is Still Right About AI


Alexander Buianov said...

Hey Louis,
I'm glad to be the first one to comment.
Thumbs up to "The Magic of Sequence Memory", "Math Is Not the Answer" and The "Brain Assumes a Perfect World".

1. What is "temporal correlations" if not sequences?
2. Could it be that patterns are just a particular case for sequences? Like flat-in-time sequences? You saying that interval can vary. Can it vary up to the zero?

In my wiev the process is generally same on every level. All the difference is in the intervals. First levels should have 0 and close to 0 intervals, while higher regions should have intervals similar to consciousness events perception(bus stopping, doors opening, peaple come out...)

Louis Savain said...

Hi Alexander,

Thanks for the comment. You write:

1. What is "temporal correlations" if not sequences?

Yes. Nodes in a sequence are certainly temporally correlated. So are concurrent spikes in a pattern. It is important to have variable intervals because multiple sequences may be correlated with one another as their speeds vary.

2. Could it be that patterns are just a particular case for sequences? Like flat-in-time sequences? You saying that interval can vary. Can it vary up to the zero?

I agree that patterns are a special case where the interval between nodes is 0. This is why they have to be treated differently. Patterns have very powerful predictive powers. For example, if a vertical line is moving from left to right across the visual field, it causes multiple pattern neurons to fire sequentially. The speed of the movement determines the interval between the firings.

In my wiev the process is generally same on every level. All the difference is in the intervals. First levels should have 0 and close to 0 intervals, while higher regions should have intervals similar to consciousness events perception(bus stopping, doors opening, peaple come out...)

I see what you are saying. However, this is not the way it works in the brain, IMO. Cortical columns at every level in the cortical hierarchy work the same way. Each column contains multiple mini-columns. All the minicolumns within a column work with the same input signals but each minicolumn responds to a different speed. The interval between nodes ranges between 10 ms and more than 200 ms. This way, a column can retain a trace of how fast it was activated.

Sinnaman said...

Your scientific views are mostly contrarian to the consensus. May I ask if there are any current scientific views in the consensus with which you agree?

Louis Savain said...

Hi Sinnaman

Thanks for the comment. The consensus is obviously not always wrong, otherwise they would be rejected. However, the consensus is almost always wrong in matters that are fundamental and important. As a Christian and a rebel, I am naturally attracted to the least beaten path. This is where the good and revolutionary stuff is.

Sinnaman said...

Thanks for replying. I just found your blog after searching about LIGO. They have a facility near where I live. A relative who lives close to the facility claims that he noticed a large difference in rainfall after they built it. Now I'm reading through your archives regarding AI and it's fascinating.

Bill said...

I'm having trouble understanding your diagram "Sequence Hierarchy". You say that nodes A and C receive inputs directly from the blue nodes labelled 1-7. But then you say the red lines are the only pathways "up" the hierarchy. Only node 7 is connected with a red line, so then what do the blue lines from nodes 1-6 represent? In the second diagram labelled "Sequence", there now appear to be sibling connections with green lines between the blue nodes. How does this relate to the previous diagram? It's not clear to me from these two pictures which signals are flowing in which directions...

Louis Savain said...

Bill, I apologise. What I wrote above was a trick to deceive some people. I purposely put out old and obsolete information out of fear that this work could fall in the wrong hands. Please read my my apology.