Skip to main content

1.55 Multi-scale defines learning

Multi-scale defines learning

https://rumble.com/vcexnm-multi-scale-defines-learning-part-1.html

https://rumble.com/vcexxw-multi-scale-defines-learning-part-2.html

Why have I been so focused on multi-scale data?  Because learning can only occur when there are multiple scales.  Why is that true, is sounds nonsensical, what is the relationship between the scale of a set of data and learning that data.  

I need to better define multi-scale systems.

A multi-scale system has at least two levels.  Each level has elements.  Yet the elements on each level are different.  How different?  In what way are they different?  Primarily the descriptive language of the elements is different.  The elements on each level describe different attributes.

Since each level creates its own descriptive language, two different levels are not able to communicate directly with each other.   Although that is a negative definition I like it.  

The positive formulation might be, a higher level is a result of a non-linear function on (multiple elements from) the lower level (this starts to sound like Christian List)

Learning as opposed to memorisation requires this creation of a new descriptive space.  This is Fernando Flores's definition of 'listening', the act of communication requires learning.

What first order and second order statistics do, such as mean and variance (and KMeans by association), is they attempt to represent the original data within the same descriptive space.  This is a poor mans memory.

Learning creates a new descriptive space, an embedding, that is unique and distinct from the original descriptive space of the data.  A model is created to map from the original descriptive space to the new descriptive space.  The result of this mapping is a new representation that cannot coexist within the original framework.

Kohonen tried to preserve a relationship across scales with spatial feature maps, yet this undermines learning!

For example, cars have wheels and a chassis.  The wheels are elements and the chassis is an element, are they are on the same level?  Well since there is no relationship between them, they are independent, I would say they are not a multi-scale system.  They are two independent systems.  

However a car is a multi-scale systems, its higher level, 'car', is composed (a function) of at least two lower level elements, wheels and chassis.

Now we can measure the attributes of the lower level data:
a) wheels have a diameter and coefficient of friction.  
b) a chassis has a passenger capacity

And the higher level data:
I) a car provides a timely service to a destination. 

It is incorrect to formulate a sentence such as, the more passengers in a chassis the quicker the car reaches its destination.  That is mixing levels.  Or the greater a wheel diameter the quicker the car reaches its destination.  

So how to create?  How to create a higher level with its own new descriptive language?  

What faddc measures is the relationship between centroids and not the relationship between data elements in the lower feature space (this I will prove later with categorical learning)

What that is akin to saying, when communicating between systems a new descriptive language is created.  

The anchor to this new language is a shared experience.  A set of two things that co-occur.  This is the Semiotic definition of a 'sign'.  When two symbols co-occur they are associated with each other and a new element (higher level element) is created, a sign.  The neurobiological way of framing that statement is to say that when two neurons fire at the same time a connection is made between them.  The statistical description might be that the distance between the two centroids is reduced if they co-occur, i.e. there is a correlation between them.

My algorithm measures the relative value of the 'Neurons' with each other.  What is the distance between two neurons as opposed to the distance between two centroids?  Centroids measure the distance in the data elements space as opposed to Neurons that measure distance in the Neuronal co-occurrence space.  Distance is not measured in absolute terms, global objective metrics like in KMeans, but in relative space at the higher level.  This creates a new descriptive space, the Neuronal space.

If we revisit the 'car' example.  A car is a complex system, that provides a unique service that its parts cannot provide.  With this new language I can communicate ideas that are unique, and can not be communicated at the lower level.  The whole is greater than the sum of its parts, a car provides a language to describe concepts that are more than just wheels and chassis.  The greater context, multiple people utilise cars, enables multiple instances of cars to be correlated and new conceptual ideas to emerge.  Thus, within the higher level language of cars I can talk about traffic, multiple cars attempting to service a destination in a timely manner.


 



Comments

Popular posts from this blog

V) How do we know we made a reasonable judgement?

V) How do we know we made a reasonable judgement? I was by my brother in NY, on my way to the airport, and I spotted a book by Umberto Eco on information and open systems.  I borrowed the book (and still have it -- sorry Jacob),  just on the whim that I would enjoy more Eco in my life.  I discovered much more, the book is Eco's earlier writing, semiotics mixed with art and science, and has had a profound affect on me.  Eco makes the argument that Shannon's description of information, a measure of the communicability of a message, provides for a measure of art. If it helps think about 'On Interpretation' by Susan Sontag, experience art without interpreting it.  There is no message not even one that we the viewer creates.   There is no meaning to be had, just an experience.  The flip side of this argument is that when there is interpretation there is meaning.  This view, proposed by Semiotics, states that when two closed systems meet and are ...

0.0 Introduction to advanced concepts in AI and Machine Learning

Introduction to advanced concepts in AI and Machine Learning I created a set of short videos and blog posts to introduce some advanced ideas in AI and Machine Learning.  It is easier for me to think about them as I met them, chronologically in my life, but I may revisit the ideas later from a different perspective. I also noticed that one of things I am doing is utilising slightly off-centre tools to describe an idea.  So for example, I employ Kohonen Feature Maps to describe embeddings.  I think I gain a couple of things this way, first it is a different perspective than most people are used to.  In addition, well you will see :-) I recommend first opening the blog entry (as per the links below), then concurrently watching the linked video. Hope you enjoy these as much as I did putting them together, David Here are links: https://data-information-meaning.blogspot.com/2020/12/memorization-learning-and-classification.html https://data-information-meaning.blogspot.com/...

III) Metrics

III) Metrics One of these things is not like the other -- but two of these things are distant from a third. I grew up with Brisk Torah, more specifically my father was a Talmid of Rabbi Joseph Soloveichik and dialectic thinking was part and parcel of our discussions.  Two things, two dinim, the rhythm in the flow between two things.  Dialectics not dichotomies.  The idea espoused by the Rambam in his description of Love and Awe, mutually exclusive, we travel between them. Why create duality?  Dialectics or dichotomies provide a powerful tool, but what is it that tool? What is the challenge? I think the Rabbinic language might be נתת דברך לשיעורים, 'your words are given to degrees', the idea being that without clear definitions we are left with vague language, something is more than something else, ok, but how much more? This I think is the reasoning for the first of the twenty one questions I was taught by my father's mother, 'is it bigger than a breadbox?',...