Editing What is Machine Learning

= What is Machine Learning =

'''Machine Learning (ML)''' is a subfield of artificial intelligence (AI) that focuses on the development of systems that can learn from data and improve their performance over time without being explicitly programmed.

== Overview ==
Machine Learning allows computers to recognize patterns, make decisions, and predict outcomes based on historical data. It contrasts with traditional programming, where rules and logic are manually coded.

== Types of Machine Learning ==

=== Supervised Learning ===
In supervised learning, the model is trained on a labeled dataset, where each input is paired with a correct output. The goal is to learn a mapping from inputs to outputs.

* Example: Email spam detection (spam or not spam)

=== Unsupervised Learning ===
Unsupervised learning involves training a model on data without labeled responses. The model tries to find hidden patterns or groupings in the data.

* Example: Customer segmentation in marketing

=== Reinforcement Learning ===
Reinforcement learning is based on agents that learn by interacting with an environment. They receive rewards or penalties based on their actions and use this feedback to learn optimal behavior.

* Example: Training a robot to walk

=== Semi-Supervised and Self-Supervised Learning ===
These approaches use a mix of labeled and unlabeled data or generate labels from the data itself. They are useful when labeling data is costly or difficult.

== Key Concepts ==

* '''Model''': A mathematical representation of a process, trained to make predictions or decisions.
* '''Training''': The process of feeding data to a model so it can learn.
* '''Features''': Input variables used for predictions.
* '''Labels''': Known outputs used in supervised learning.
* '''Overfitting''': When a model performs well on training data but poorly on new data.
* '''Generalization''': The model’s ability to perform well on unseen data.

== Applications ==

* '''Speech recognition''' (e.g., Siri, Google Assistant)
* '''Image recognition''' (e.g., facial recognition)
* '''Recommendation systems''' (e.g., Netflix, Amazon)
* '''Medical diagnosis'''
* '''Fraud detection'''
* '''Autonomous vehicles'''

== Advantages ==

* Can identify complex patterns in large datasets
* Improves with more data and training
* Enables automation of tasks previously requiring human intelligence

== Limitations ==

* Requires large amounts of quality data
* Can be biased if training data is biased
* Interpretability of complex models (e.g., neural networks) can be difficult

== Related Pages ==
* [[Artificial Intelligence]]
* [[Deep Learning]]
* [[Data Science]]
* [[Neural Network]]

== References ==
<references />

[[Category:Machine Learning]]
[[Category:Artificial Intelligence]]