Artificial Intelligence Notes
Neuromorphic
- Start with a neural net with N Inputs, NxN hidden layers and N outputs
- Choose perceptron behavior
- Assign weights and biases stochastically [0.0, 1.0]
- Feed inputs [0.0, 1.0]
- Observe output [0.0, 1.0]
- Learn (Gradient descent)
Thoughts
- What is curiosity? A strong desire to know or learn something.
- What is knowledge? Facts, information, and skills acquired through experience or education; the theoretical or practical understanding of a subject.
- What is learning? The acquisition of knowledge or skills through study, experience, or being taught.
- What is imagination? The faculty or action of forming new ideas, or images or concepts of external objects not present to the senses.
- What is creativity? The use of imagination or original ideas to create something.
- What is intuition? The ability to acquire knowledge without proof, evidence, or conscious reasoning, or without understanding how the knowledge was acquired.
- What is science? The intellectual and practical activity encompassing the systematic study of the structure and behavior of the physical and natural world through observation and experiment.
- What is philosophy? The study of the fundamental nature of knowledge, reality, and existence, especially when considered as an academic discipline.
- What is a pattern? A discernible coherent system based on the intended interrelationship of component parts.
- Are there different form of creativity? Artistic and scientific creativities
- What is discovery and invention?
- Evolution and adaptation haphazard learning method
- A system that accumulates knowledge
- Learn by analogy, pattern recognition
GAI (General Artificial Intelligence)
Is there a fundamental pattern to learning? Is there a fundamental pattern to discovery?
One thing is to know another is being able to do it.
Artificial Intelligence
Machine Learning
Deep Learning
Philosophical consequences
Endowing a machine of intuition sets the stage for geometric evolution
Force Field Computing
- Imagine a system of particles described by N properties p(x1, x2, … xN)
- Imagine a space subject to M force fields each acting on properties Fm()
- Shake (vibrate) the system
- The individual particles will eventually sattle in a pattern
Last update 2018-12-11 06:26