Machine learning (ML) and Deep learning - Revision history

Root at 08:27, 1 November 2025

2025-11-01T08:27:39Z

← Older revision		Revision as of 09:27, 1 November 2025
Line 68:		Line 68:
	<p>Hierarchical models that split data based on feature thresholds. Easy to interpret but prone to overfitting.		<p>Hierarchical models that split data based on feature thresholds. Easy to interpret but prone to overfitting.
	</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121908.png\|292x292px]]		</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121908.png\|292x292px]]

			[[Machine learning algorithms#decision trees\|Here is a practical example]]

	== Other algorithms & examples ==		== Other algorithms & examples ==

Root at 08:26, 1 November 2025

2025-11-01T08:26:14Z

← Older revision		Revision as of 09:26, 1 November 2025
Line 69:		Line 69:
	</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121908.png\|292x292px]]		</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121908.png\|292x292px]]

	== Other algorithms ==		== Other algorithms & examples ==
	* '''Random Forests:''' Ensembles of decision trees averaged to improve generalization.		Check in detail these algorithms and real implementations in python [[Machine learning algorithms\|here]]
	* '''Support Vector Machines (SVM):''' Classify data using hyperplanes that maximize margin between classes.

	~~----~~

	= Deep learning: neural networks and perceptrons =		= Deep learning: neural networks and perceptrons =
Line 125:		Line 122:

	While AGI remains aspirational, advances in foundation models, reinforcement learning, and embodied AI point toward incremental progress.		While AGI remains aspirational, advances in foundation models, reinforcement learning, and embodied AI point toward incremental progress.
	[[Category:KC AI technical aspects]]		[[index.php?title=Category:KC AI technical aspects]]

Root at 08:56, 28 October 2025

2025-10-28T08:56:16Z

← Older revision		Revision as of 09:56, 28 October 2025
Line 47:		Line 47:
	<span id="classical-machine-learning-methods"></span>		<span id="classical-machine-learning-methods"></span>

	= ~~Classical machine~~ learning algorithms =		= Machine learning algorithms =
	== Linear Regression ==		== Linear Regression ==
	<p>Models continuous outcomes using linear relationships.		<p>Models continuous outcomes using linear relationships.
	</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121721.png\|225x225px]]		</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121721.png\|225x225px]]

	[[~~Python modules~~#linear regression ~~example~~\|Here it is a practical example]]		[[Machine learning algorithms#linear regression\|Here it is a practical example]]

	== Logistic Regression ==		== Logistic Regression ==
Line 58:		Line 58:
	</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121807.png\|275x275px]]		</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121807.png\|275x275px]]

	[[~~Python modules~~#logistic regression\|Here is a practical example]]		[[Machine learning algorithms#logistic regression\|Here is a practical example]]

			== K-Nearest Neighbors (KNN) ==
			K-Nearest Neighbors (KNN) is a '''supervised classification algorithm''' used to estimate the probability that an element X belongs to a class C, based on its proximity to other known examples in the dataset.
			[[File:Ml algorithm knn.jpg\|none\|thumb]]
			[[Machine learning algorithms#K-Nearest Neighbors (KNN)\|Here is a practical example]]

	== Decision Trees ==		== Decision Trees ==
	<p>Hierarchical models that split data based on feature thresholds. Easy to interpret but prone to overfitting.		<p>Hierarchical models that split data based on feature thresholds. Easy to interpret but prone to overfitting.
	</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121908.png\|292x292px]]~~</p>~~		</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121908.png\|292x292px]]

	== Other algorithms ==		== Other algorithms ==
	* '''Random Forests:''' Ensembles of decision trees averaged to improve generalization.		* '''Random Forests:''' Ensembles of decision trees averaged to improve generalization.
	* '''Support Vector Machines (SVM):''' Classify data using hyperplanes that maximize margin between classes.		* '''Support Vector Machines (SVM):''' Classify data using hyperplanes that maximize margin between classes.
	* '''k-Nearest Neighbors (kNN):''' Classifies based on similarity (distance metrics) to nearby samples.

	----		----

	= ~~Neural Networks~~ and ~~Perceptrons~~ =		= Deep learning: neural networks and perceptrons =
	Neural networks, inspired by the brain, use algorithmic nodes (perceptrons) arranged in layers to perform complex computations.		Neural networks, inspired by the brain, use algorithmic nodes (perceptrons) arranged in layers to perform complex computations.

Line 85:		Line 89:
	</li></ul>		</li></ul>

	= ~~Deep Learning: multi~~-layered perceptrons and beyond =		== Multi-layered perceptrons and beyond ==
	Multiple perceptron layers, arranged differently, expand machine learning into deep learning.		Multiple perceptron layers, arranged differently, expand machine learning into deep learning.

Root: /* Logistic Regression */

2025-10-28T08:25:45Z

Logistic Regression

← Older revision		Revision as of 09:25, 28 October 2025
Line 57:		Line 57:
	<p>Models binary or multi-class outcomes via a sigmoid function mapping. Useful for predicting the probability of anything being true or false.		<p>Models binary or multi-class outcomes via a sigmoid function mapping. Useful for predicting the probability of anything being true or false.
	</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121807.png\|275x275px]]		</p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-121807.png\|275x275px]]

			[[Python modules#logistic regression\|Here is a practical example]]

	== Decision Trees ==		== Decision Trees ==

Root: Root moved page Machine learning and Deep learning to Machine learning (ML) and Deep learning without leaving a redirect

2025-10-25T11:23:56Z

Root moved page Machine learning and Deep learning to Machine learning (ML) and Deep learning without leaving a redirect

← Older revision	Revision as of 12:23, 25 October 2025
(No difference)

Root at 11:17, 25 October 2025

2025-10-25T11:17:54Z

@@ Line 23: / Line 23: @@
 Self-learning agents require exploration–exploitation balance (ε-greedy, entropy regularization) and stability mechanisms such as experience replay.
 = The machine learning process =
@@ Line 71: / Line 44: @@
 Data → Cleaning → Training/Test Split → Training Model → Testing Model → Validation → Final Model
 = Neural Networks and Perceptrons =
@@ Line 83: / Line 80: @@
 <li><p>'''Output layer:''' Produces the final prediction or classification.<br />
 </p>
-<p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-122035.png|326px|center]]</p></li></ul>
+<p>[[File:UserDocumentation_Knowledge_Central_KC_Global_KC_AI_KC_AI_technical_aspects_Machine_learning_and_Deep_learningimage-20251017-122035.png|326x326px]]</li></ul>
 </li></ul>
 = Deep Learning: multi-layered perceptrons and beyond =

Root at 07:35, 24 October 2025

2025-10-24T07:35:12Z

@@ Line 26: / Line 26: @@
 <span id="classical-machine-learning-methods"></span>
-= Classical Machine Learning methods =
+= Classical machine learning methods =
 ML tools include logical and statistical models such as decision trees, linear regression, and logistic regression.
@@ Line 51: / Line 51: @@
 * '''k-Nearest Neighbors (kNN):''' Classifies based on similarity (distance metrics) to nearby samples.
-<span id="neural-networks-and-perceptrons"></span>
+= The machine learning process =
 = Neural Networks and Perceptrons =

Root at 11:32, 22 October 2025

2025-10-22T11:32:18Z

Show changes

Maintenance script: Added category KC AI technical aspects

2025-10-19T17:50:50Z

Added category KC AI technical aspects

← Older revision		Revision as of 18:50, 19 October 2025
Line 133:		Line 133:
	<!-- From bodyContent 52625434.mraw -->		<!-- From bodyContent 52625434.mraw -->

			[[Category:KC AI technical aspects]]

Maintenance script: Maintenance script moved page UserDocumentation:Knowledge Central/KC Global/KC AI/KC AI technical aspects/Machine learning and Deep learning to Machine learning and Deep learning: Cleaned title and categorized

2025-10-19T17:50:49Z

Maintenance script moved page UserDocumentation:Knowledge Central/KC Global/KC AI/KC AI technical aspects/Machine learning and Deep learning to Machine learning and Deep learning: Cleaned title and categorized

← Older revision	Revision as of 18:50, 19 October 2025
(No difference)