Uncategorized

Alan Kay

Alan Kay

Alan Kay

“Don’t worry about what anybody else is going to do… The best way to predict the future is to invent it. Really smart people with reasonable funding can do just about anything that doesn’t violate too many of Newton’s Laws!”
— Alan Kay

What is machine learning?

Any process by which a system improves performance from experience — Herbert Simon

Machine learning overview

Machine learning overview

Machine learning refers to the ability of computers to automatically acquire new knowledge, learning from, for example, past cases or experience, from the computer’s own experiences, from exploration, or from direct input of knowledge by the system users. Machine learning enables computer software to adapt to changing circumstances, enabling it to make better decisions than non-AI software.

The diagram presents an overview of machine learning. The center-most area depicts techniques and algorithms for pattern detection. The middle region lists reasoning methodologies. The outer-most part of the diagram identifies application areas and activities where machine learning applies today.

What is a model?

A representation of an actual or conceptual system.

Examples of models

Examples of models

A model is a representation of an actual or conceptual system that involves mathematics,
logical expressions, or computer simulations that can be used to predict how the system might perform or survive under various conditions or in a range of hostile environments.

A simulation is a method for implementing a model. It is the process of conducting experiments with a model for the purpose of understanding the behavior of the system modeled under selected conditions or of evaluating various strategies for the operation of the system within the limits imposed by developmental or operational criteria. Simulation may include the use of analog or digital devices, laboratory models, or “testbed” sites.

Semantic networks are building blocks of knowledge models

Semantic networks are building blocks of knowledge models

A semantic network is comprised of three basic elements:

  • Concepts are any ideas or thoughts that have meaning
  • Relations describe specific kinds of links or relationships between two concepts
  • Instances (of a relationship) consist of two concepts linked by a specific relation.

Relationships in a semantic network go beyond the standard broader than, narrower than, or
related terms of thesauri. They may include specific whole-part relationships, cause-effect, parent-child, and many, many others.

Knowledge models in direct model execution systems have strongly typed concepts and relationships.

Knowledge models in direct model execution systems have strongly typed concepts and relationships.

How do humans encode thoughts, represent knowledge, and share meanings?

Using patterns and language.

Saul Steinberg — Labrynth

Saul Steinberg — Labrynth

Patterns are knowledge units. A pattern is a compact and rich in semantics representation of raw data. Semantic richness is the knowledge a pattern reveals that is hidden in the huge quantity of data it represents. Compactness is the correlations among data and the synthetic, high level description of data characteristics. For example, an image.

Language is a system of signs, symbols, gestures, and rules used in communicating. Meaning is something that is conveyed or signified. Humans have plenty of experience encoding thoughts and meanings using language in one form or another… Our proficiency varies. We tend to be better at some kinds of language, and not so good at others.

Five forms of human language

Five forms of human language

Human endeavors often combine different skills and expertise, e.g. to make a movie; design and construct a building; or coordinate response to an emergency. The following table gives examples of five forms of human language: natural, visual, formal, behavioral, and sensory language.

How is knowledge different from content?

Content is merely an expression of knowledge.

Source: Pieter Bruegel, Tower of Babel

Source: Pieter Bruegel, Tower of Babel

Content is not knowledge. Knowledge can be separated from content, just as content can be separated from format. The difference between content and knowledge is the difference between form and substance. Content is always specific. Knowledge is always generic and structural. The same knowledge can take many forms. Content is a language, audience, media, and situation-specific rendition of knowledge.