Keywords
Machine Learning, Fuzzy Logic, Neural Networks
CCS Concepts
CS.HCI(HUMAN COMPUTER INTERFACE), CS.MACHINE TEACHING
Short Introduction
In Reality, Its unusual to find a gap between Artificial Intelligence and Machine Learning were AI is dedicated to Algorithms and Machine Learning is concerned with Principles and errors and both needed data for Validating so called issues, But we came across something interesting topic so called Machine Teaching, were it is a concept related to fill the gap of artificiality or its trajectory
Methodology
Its an Hypothetical Assumption, since this predicted possibilities resides between Artificial Intelligence and Machine Learning concepts, in other words its a barrier between reality and imaginary
mathematical expression is followed by
f(x,y)= cos(x)+ |sin(y)| -> Real + Imaginary,
=> f(z)=a+i*b where a, b are assumed as binary keys where x ,y are real and imaginary planes in two dimensional space
Expected Results
Its obvious that we are considering an assumption with certain restrictions to avoid misconceptions, so basically validation of Fuzzy weights a, b resides in real and imaginary planes and moreover Predicted thoughts(Imitation based)are defined with binary values '1','0' for instance.
if value is 1 then fuzzy values is 0 0 1
else value is 2 then fuzzy values is 0 1 0
else if value is 3 then fuzzy value is 1 0 0
- fuzzy values defines fuzzy weights based on neural schema
- fuzzy values or inputs are conceptual values based on hypothetical assumptions used to quantify fuzzy weights.
Conclusions
In the time domain, Logical thinking is based on Assumption of thought process as imaginary (captured within sinusoidal wave) and imitations (cosine) as real towards evolution of predicted one may be logical reasoning. To be noted that, cosine as delayed and sinusoidal as wave within time, therefore complexity of proposed approach is based on originality and assumed one.
Noted Facts