Artificial Intelligence - Revision history

Hdridder: /* Supervised */

2019-04-28T09:34:24Z

Supervised

← Older revision		Revision as of 09:34, 28 April 2019
Line 9:		Line 9:

	===Supervised===		===Supervised===
	~~Feed~~ input/~~output pairs~~		Learning from a training set. A training set has m samples of x's (input variables or features) and the resulting y's (output/target variables)

	====Regression problems====		====[[AI:Regression_Problems\|Regression problems]]====
	Predict real-valued output. Find a formula to get from the input attributes to the output.		Predict real-valued output. Find a formula to get from the input attributes to the output.

Hdridder at 13:31, 22 April 2019

2019-04-22T13:31:15Z

@@ Line 10: / Line 10: @@
 ===Supervised===
 Feed input/output pairs
 ===Unsupervised===
 Input only. The system learns from finding commonalities in the data presented.
@@ Line 26: / Line 43: @@
 ===Generative===
 The system understands language and can generate answers itself.

Hdridder: /* Problem types */

2019-04-22T13:29:16Z

Problem types

← Older revision		Revision as of 13:29, 22 April 2019
Line 28:		Line 28:


	=Problem types=		=Problem types for supervised learning.=

	==Regression==		==Regression==

Hdridder at 19:12, 6 April 2019

2019-04-06T19:12:37Z

← Older revision		Revision as of 19:12, 6 April 2019
Line 1:		Line 1:
			[[Category:AI]]
	=Types of AI=		=Types of AI=
	==Symbolic==		==Symbolic==
Line 27:		Line 28:


			=Problem types=

			==Regression==
			Predict real-valued output. Find a formula to get from the input attributes to the output.

			==Classification==
			Find a discrete value from the input data. Is this of type A, B or C

	~~=Classification=~~
	* Features and labels		* Features and labels
	: The system is trained with labeled text is split in features. The features get a weight.		: The system is trained with labeled text is split in features. The features get a weight.

Hdridder at 20:30, 9 October 2018

2018-10-09T20:30:49Z

@@ Line 1: / Line 1: @@
-types of AI
+=Types of AI=
 ==Symbolic==
 Trying to capture intelligence in rules (Marvin Minsky, John McCarthy, Oliver Selfridge, Ray Solomonoff)
@@ Line 14: / Line 14: @@
 ===Reinforcement===
 Input and Critic. Constant feeding of new data, try to evaluate and have the result checked (by humans).

Hdridder: /* Unsupervised */

2018-10-09T19:22:59Z

Unsupervised

← Older revision		Revision as of 19:22, 9 October 2018
Line 10:		Line 10:
	Feed input/output pairs		Feed input/output pairs
	===Unsupervised===		===Unsupervised===
	Input only		Input only. The system learns from finding commonalities in the data presented.

	===Reinforcement===		===Reinforcement===
	Input and Critic. Constant feeding of new data, try to evaluate and have the result checked (by humans).		Input and Critic. Constant feeding of new data, try to evaluate and have the result checked (by humans).

Hdridder: Created page with "2 types of AI ==Symbolic== Trying to capture intelligence in rules (Marvin Minsky, John McCarthy, Oliver Selfridge, Ray Solomonoff) ==Subsymbolic== Learn to understand the wor..."

2018-09-30T14:34:54Z

Created page with "2 types of AI ==Symbolic== Trying to capture intelligence in rules (Marvin Minsky, John McCarthy, Oliver Selfridge, Ray Solomonoff) ==Subsymbolic== Learn to understand the wor..."

New page

2 types of AI
==Symbolic==
Trying to capture intelligence in rules (Marvin Minsky, John McCarthy, Oliver Selfridge, Ray Solomonoff)
==Subsymbolic==
Learn to understand the world by trial and error. (Rosenblatt).

Neural Network, later called Machine Learning.

===Supervised===
Feed input/output pairs
===Unsupervised===
Input only
===Reinforcement===
Input and Critic. Constant feeding of new data, try to evaluate and have the result checked (by humans).