Sunday, February 25, 2018

Fast Cortical Learning Using Spike Timing


Previously, I argued that cortical feedback connections were essential to handling sensory uncertainty and to cortical learning. In this article, I delve further into how learning works in the cortex. But, first, a word about the Yin-Yang brain.

The Yin-Yang Brain and the Attention Problem

We must keep in mind that the cortex in each hemisphere of the brain actually consists of two mirror opposite hierarchies. That is to say, every cortical column has a complement or opposite column. Although logically linked, the two reside in separate but complementary hierarchies (trees). The same is true for the minicolumns within the columns. If a connection is made to one minicolumn, a complementary connection is automatically made to its opposite. This Yin-Yang architecture also applies to the thalamus (which is where elementary pattern detectors are) and the rest of the brain.

Yin-Yang Brain
The main reason for having a Yin-Yang brain is that we live in a Yin-Yang reality. It is for this reason that biological sensors and effectors come in complementary-opposite pairs. Another reason has to do with attention, the ability to focus on one object while ignoring all others. As I will explain in a future article, the brain has an efficient way to cluster a large number of elements to form a single object. Clustering is crucial to invariant object detection and ultimately to survival. This is an unsolved problem in mainstream AI. The brain uses precise timing to solve the problem: It assumes that all the elements that comprise an object are temporally correlated. The flaw in this solution is that opposite phenomena are not temporally correlated. For example, the motion of an object moving left in the field of view is not temporally correlated with its motion to the right. In fact, the two phenomena do not use the same sensors and pattern detectors. Thus the correlation is not temporal but logical. This is not something that is learned. The brain has innate neuronal mechanisms to handle Yin-Yang logic and thereby marry two opposites into one entity.

For the sake of clarity, I will assume in this article that there is only one hierarchy.

Function and Organization of Sequence Memory

The main function of sequence memory is to combine lots of small elementary patterns into arbitrarily complex objects on the fly, even objects that it has never seen before. It is called sequence memory because the building blocks (minicolums) of the objects are also nodes in highly predictive sequences. Like pattern memory, sequence memory is a hierarchical, feedforward, multilayer, unsupervised, spiking neural network. The bottom layer receives input signals directly from pattern memory. Every layer in the hierarchy, except the top layer, sends outputs to the layer right above it.

Sequence memory consists of a large number of work-alike neuronal structures called cortical columns or macrocolumns. The main function of cortical columns is to detect unique combinations of patterns as they occur. Each column consists on average of 100 minicolumns, each of which attempts to learn a unique pattern combination.
Note: I modified the cortical column diagram that I used in the previous article to better show all the inputs, outputs and feedback connections.
Cortical Column with 5 Minicolumns
As seen above, every minicolumn has 1 feedforward output and 7 inputs (6 associate inputs and 1 primary input). The primary input of a cortical column is the only input that is common to all the minicolumns within that column. Inputs to a column originate from either pattern memory or another level in the sequence hierarchy. Outputs are connected to the level immediately above if any. Every input or output connection is paired with a feedback connection. This means that each minicolumn has 1 feedback input connection (green) from the layer immediately above its own and 7 output feedback connections (blue) that send signals down the hierarchy.

Learning in Sequence Memory

Learning in sequence memory is not about finding sequences but about finding pattern combinations around a central or primary pattern. These combinations are stored in the minicolumns. Once a minicolumn is populated and operational, it can become an actual node in a sequence or even in multiple sequences (topic for a future post). The learning process assumes that the following conditions are met:
  • There is an existing population of cortical columns waiting for input connections.
  • There are a number of pattern detectors or minicolumns that have no output connections.
Here are the learning rules:
  • A small percentage of inputs from either pattern detectors or minicolumns are chosen randomly to be the primary inputs of the cortical columns. The rest will be associate inputs.
  • A pattern detector or minicolumn can only make one output connection to a target minicolumn.
  • Within any column, learning advances one minicolumn at a time.
  • Only perfect pattern signals are used for learning.
  • A signal from a minicolumn is considered good enough if the equivalent of two or more of its connections fired.
  • An input connection to a minicolumn immediately passes the test if it fires concurrently with all existing inputs on that minicolumn.
  • Once a minicolumn has acquired all seven inputs, it is considered mature and learning continues with another minicolumn in the parent column. Unless they are located at the top level, fully populated minicolumns send their output connections up the hierarchy where the same learning method is used.
Keep in mind that this learning method will make bad connections every once in a while. As I explained in the previous article, the brain gets rid of bad cortical connections during REM sleep.


Learning in sequence memory is extremely fast for several reasons. First, a connection needs only pass the concurrence test once. Second, the connection is not severed if it fails the test; it can be tested on the same minicolumn multiple times. Finally, a huge number of connections can be tested simultaneously. The requirement that a minicolumn fires if only an equivalent of 2 or more of its input connections fire is very powerful. This is what allows us to recognize abstract art and see objects in the clouds. How the equivalence is computed is slightly more complicated than it sounds but I'll leave that to a future post. Stay tuned.

See Also:

Solving the Mysteries of Reciprocal Corticothalamic Feedback and Cortical Learning


Peter ( said...

Extremely informative Louis, very interesting. Thanks for posting.

The yingyan approach in particular. I wonder though, sorry if I sound stupid, what about up/down and any other random direction an object can move in? If you never saw this particular object moving up/down you are not able to identify it just by left/right logic right?

Louis Savain said...

Hi Peter,

I picked the left-right motion as an example but the problem is the same for any orientation. Your question is one that had actually stumped me in the past. I concluded that the brain is able to identify an object moving in any direction because of the center-surround design of the retina. Movement in any direction will not only activate pattern detectors tuned to that direction but also detectors tuned to other directions, but at different speeds. This creates temporal correlations that the visual cortex can use for clustering. This is why our eyes continually move in microsaccades in various directions. Without the microsaccades, our vision would be seriously limited. Some animals do not have microsaccades and they are easy prey for predators that exploit their visual limitation.

The Yin-Yang structure of the brain is evident in certain optical illusions. This particular illusion, for example, fools the visual system into seeing a spiral even though there are only circles in the image. The illusion disappears if half of the image is occluded with a piece of paper. It does not matter which half.

Louis Savain said...

By the way, someone recently accused me of claiming special knowledge. I make no such claim. I received no special knowledge from God or anyone else to brag about.

I am a Christian researcher and I research ancient occult Biblical texts that, I believe, contain revolutionary scientific knowledge for our age. My interpretations have been wrong many times and I have had to retrace my steps on many occasions. I have made progress but some of my current assumptions may still be wrong. Heck, others might be able to do a much better job at it than I have.

Also, I don't write for the world. I write only for believers. If my approach to understanding the brain and intelligence bothers anyone, then obviously, it is not meant for you. Sorry.

I just thought I'd get this off my chest.

Louis Savain said...

Note: I made a slight correction to article after noticing a redundancy at the end of the paragraph on learning in sequence memory.

Unknown said...

Is it possible for you to post a video on youtube that demos the capabilities of your approach? I'd really like to see it. I know you are paranoid, but a video shouldn't give away too much. I'm just very interested in seeing what you have.

Louis Savain said...

Is it possible for you to post a video on youtube that demos the capabilities of your approach?

Sorry. Can't do that. Not yet anyway. I'm working on a mobile app for the hearing impaired and I'm still debating whether or not I should publish it. I cherish my crackpot reputation because it keeps me under the radar of certain undesirable people and organizations.

Chuck Smith said...

my hearing is terrible, is your system able to help those with poor hearing orno hearing?