Sunday, February 18, 2018

Stuff I've Been Working on: The Cortical Column


The Cortical Column

Understanding the organization and function of the cortical column is essential to figuring out how the brain works. What follows are partial results of my brain/intelligence research over the years. Unlike deep neural nets, the brain can instantly see a complex object that it has never seen before. How does it do it? It learns lots of small elementary patterns (lines, edges, bits of sounds, etc.) by creating simple sensors that reside in the thalamus.

All elementary patterns come in opposite/complementary pairs. They are the building blocks of all objects. The brain can instantly reuse them to detect any complex object on the fly. This is crucial to survival. Object detection is the job of millions of cortical columns. These are organized into two yin-yang or mirror hierarchies of up to 20 levels. The object detection process is fast and simple and requires little computation. Signals from pattern detectors simply percolate up the hierarchy according to their temporal signatures. An entire detection process, from elementary pattern detections to recognition feedback signals, takes about 10 milliseconds.

Each column can learn dozens of small pattern combinations stored in minicolumns. The combinations in every column revolve around a single pattern detector called the primary input. Only one combination can be detected at a time. Each minicolumn has one output that is sent to a higher layer. Each also receives a feedback connection from the layer above it. Feedback signals are recognition events that serve to correct incomplete pattern detections. How the combinations are learned is the topic for a future article.

The cortical hierarchy is a magnificent machine. It can do all sorts of beautiful and wonderful things that I cannot go into in this article. I will conclude by adding that an activated topmost minicolumn in the knowledge tree (a branch) represents a complex sensed object or pattern at a point in time.

I don't know when but there will be more to come. Stay tuned.

I'm Working on Stuff

A Little Taste of What I'm Working On

That's all.

Friday, February 9, 2018

Busy Days

I'm Still Alive

I'm just busy developing a smartphone application for the hearing impaired market. It's slow going but I'm hoping I can use it to raise enough money for much bigger robotics projects I have planned for the future. Stay tuned.

Friday, February 2, 2018

People Ask Me, What Do You Have Against Deep Learning?

Neurons
Yes, I Cannot Stand Deep Learning

I got a closetful of criticisms against deep learning. I have written about them in the past. I will not list them here because what would be the point? I am not really against the technology of deep learning per se. It is useful for what it does. I am just against the idea advanced by mainstream AI that deep learning is a step toward artificial general intelligence (AGI) or human-like intelligence. In this context, let me just say that, if you are researching AGI, deep learning must be thrown away like yesterday's garbage for this one specific reason if for no other: A deep neural net learns complex patterns but the brain does not. The brain can instantly see a new complex pattern without learning it. Let me say this again for emphasis because it is crucial to my position:
A deep neural net learns complex patterns but the brain does not. The brain can instantly see a new complex pattern without learning it.
Huh? That's right. In fact, almost everything the brain sees is new, that is, seen from different angles or under different lighting conditions. There aren't enough neurons and synapses in the brain to store all the possible patterns that it would need to learn in order to interact with the world. We can instantly see complex objects or patterns that we have never seen before. A deep learning system would be blind to them. We only remember high level bits and pieces of the patterns that we see. Most of the low level details are either forgotten or are written over by new experiences.

As the late philosopher and AI critic, Hubert Dreyfus, was fond of saying, the brain does not model the world. The world is its own model. The brain simply learns how to see it. There is huge difference between the two, one that I hope will, one day, be common knowledge in the scientific community. Dreyfus was saying this decades ago. He was at least a hundred years ahead of mainstream AI.

See Also:

The World Is its Own Model or Why Hubert Dreyfus Is Still Right About AI

Friday, January 26, 2018

A Surprising Secret About Sequence Learning in the Brain

This Is Not the Way It Works

Note: This article is not meant for atheists or materialists. It is for believers only. Sorry.

When thinking about how sequence learning might work in the brain, most people would imagine some sort of neuronal mechanism that strings activated nodes (minicolums) together, as one would string pearls to form a necklace. Well, this is not the way it works. Surprisingly, the brain has no special mechanism for sequence learning. The brain forms the pearls that will go in the necklace but does not string them together. Sequence learning occurs automatically. That is to say, the pearls know where they belong in their sequence. It gets even better. If the order of the sequence changes for whatever reason, the pearls will automatically rearrange their positions. How is that possible?

The Timer

The trick is to use a timer. I have always maintained that the brain is essentially a massive timing mechanism. The hippocampus can generate special spike trains that are sent out to the cortex and used for timing purposes. When a node is activated, the time of its activation is immediately recorded and the node is given an initial activation strength. This is what neurobiologists and psychologists refer to as a memory trace. Unless reawakened multiple times and strengthened, the trace dissipates and the memory is gone. What is interesting is that, during recollection, the brain can use the same spike trains internally to reactivate the nodes in the exact order in which they were activated.
Wake up, and strengthen the things that remain, which were about to die; for I have not found your deeds completed in the sight of My God. So remember what (how) you have received and heard; and keep it, and repent. Therefore if you do not wake up, I will come like a thief, and you will not know at what hour I will come to you.

Rev 3:2-3, Message to Sardis
Enjoy.

Friday, January 19, 2018

Re: The High Priest, the Golden Menorah and the Cortical Column

I apologise for taking down the previous article about the cortical column. I just don't think it is the right time for that knowledge to be released. Not yet. Sorry.

Friday, January 12, 2018

I Understand the Cortical Column

Just a quick post for the record. My original model of the cortical column was in error. The column does not represent a sequence of nodes, as I assumed back then, but a single node in a long sequence. Each minicolumn is a different manifestation of that one node. I was right about one thing: only one minicolumn can be activated at a time. The activation of a minicolumn is very deterministic and highly predictive: it has only one successor and one predecessor. That's all for now.

Have a good weekend.