Supervised learning - Revision history

Designing Buildings at 07:25, 10 July 2024

2024-07-10T07:25:47Z

← Older revision		Revision as of 07:25, 10 July 2024
Line 1:		Line 1:
−	A way of training machine learning systems for a specific application. In a training phase, an AI system is fed labelled data. The system trains from the input data, and the resulting model is then tested to see if it can correctly apply labels to new unlabelled data (such as if it can correctly label unlabelled pictures of cats and dogs accordingly). This type of learning is useful when it is clear what is being searched for, such as identifying spam mail.	+	Supervised learning is a way of training machine learning systems for a specific application. In a training phase, an AI system is fed labelled data. The system trains from the input data, and the resulting model is then tested to see if it can correctly apply labels to new unlabelled data (such as if it can correctly label unlabelled pictures of cats and dogs accordingly). This type of learning is useful when it is clear what is being searched for, such as identifying spam mail.

	Semi-supervised [https://www.designingbuildings.co.uk/wiki/Learning l]earning also a way of training machine learning systems for a specific application, is where an AI system uses a mix of supervised and unsupervised learning and labelled and unlabelled data. This type of learning is useful when it is difficult to extract relevant features from data and when there are high volumes of complex data, such as identifying abnormalities in medical images, like potential tumours or other markers of diseases. See also supervised learning, unsupervised learning, reinforcement learning and training datasets.		Semi-supervised [https://www.designingbuildings.co.uk/wiki/Learning l]earning also a way of training machine learning systems for a specific application, is where an AI system uses a mix of supervised and unsupervised learning and labelled and unlabelled data. This type of learning is useful when it is difficult to extract relevant features from data and when there are high volumes of complex data, such as identifying abnormalities in medical images, like potential tumours or other markers of diseases. See also supervised learning, unsupervised learning, reinforcement learning and training datasets.
Line 30:		Line 30:
	Will AI ever be able to design buildings?		Will AI ever be able to design buildings?

−	[[Category:DCN_Dataset]] [[Category:DCN_Definition]] [[Category:DCN_Software]] [[Category:Definitions]]	+	[[Category:DCN_Dataset]] [[Category:DCN_Definition]] [[Category:DCN_Software]] [[Category:Definitions]] [[Category:BIM]]

Editor at 18:42, 9 July 2024

2024-07-09T18:42:13Z

← Older revision		Revision as of 18:42, 9 July 2024
Line 1:		Line 1:
−	A way of training machine learning systems for a specific application. In a training phase, an AI system is fed labelled data. The system trains from the input data, and the resulting model is then tested to see if it can correctly apply labels to new unlabelled data (such as if it can correctly label unlabelled pictures of cats and dogs accordingly). This type of learning is useful when it is clear what is being searched for, such as identifying spam mail~~. See also semi-supervised learning, unsupervised learning, reinforcement learning and training datasets~~.	+	A way of training machine learning systems for a specific application. In a training phase, an AI system is fed labelled data. The system trains from the input data, and the resulting model is then tested to see if it can correctly apply labels to new unlabelled data (such as if it can correctly label unlabelled pictures of cats and dogs accordingly). This type of learning is useful when it is clear what is being searched for, such as identifying spam mail.

−	~~That~~ is ~~opposed~~ to supervised learning another way of training machine learning systems for a specific application. An AI system is fed large amounts of unlabelled data, in which it starts to recognise patterns of its own accord. This type of learning is useful when it is not clear what patterns are hidden in data, such as in online shopping basket recommendations (“customers who bought this item also bought the following items”)~~. See also semi-supervised learning, supervised learning and reinforcement learning and training datasets~~.	+	Semi-supervised [https://www.designingbuildings.co.uk/wiki/Learning l]earning also a way of training machine learning systems for a specific application, is where an AI system uses a mix of supervised and unsupervised learning and labelled and unlabelled data. This type of learning is useful when it is difficult to extract relevant features from data and when there are high volumes of complex data, such as identifying abnormalities in medical images, like potential tumours or other markers of diseases. See also supervised learning, unsupervised learning, reinforcement learning and training datasets.
		+
		+	Unsupervised learning another way of training machine learning systems for a specific application. An AI system is fed large amounts of unlabelled data, in which it starts to recognise patterns of its own accord. This type of learning is useful when it is not clear what patterns are hidden in data, such as in online shopping basket recommendations (“customers who bought this item also bought the following items”).

	This appears in the [https://www.designingbuildings.co.uk/wiki/Uk_government UK Government] website as '[https://post.parliament.uk/artificial-intelligence-ai-glossary/ Artificial intelligence (AI) glossary]' dated January 2024.		This appears in the [https://www.designingbuildings.co.uk/wiki/Uk_government UK Government] website as '[https://post.parliament.uk/artificial-intelligence-ai-glossary/ Artificial intelligence (AI) glossary]' dated January 2024.

Editor: Created page with "A way of training machine learning systems for a specific application. In a training phase, an AI system is fed labelled data. The system trains from the input data, and the resu..."

2024-07-09T17:36:37Z

Created page with "A way of training machine learning systems for a specific application. In a training phase, an AI system is fed labelled data. The system trains from the input data, and the resu..."

New page

A way of training machine learning systems for a specific application. In a training phase, an AI system is fed labelled data. The system trains from the input data, and the resulting model is then tested to see if it can correctly apply labels to new unlabelled data (such as if it can correctly label unlabelled pictures of cats and dogs accordingly). This type of learning is useful when it is clear what is being searched for, such as identifying spam mail. See also semi-supervised learning, unsupervised learning, reinforcement learning and training datasets.

That is opposed to supervised learning another way of training machine learning systems for a specific application. An AI system is fed large amounts of unlabelled data, in which it starts to recognise patterns of its own accord. This type of learning is useful when it is not clear what patterns are hidden in data, such as in online shopping basket recommendations (“customers who bought this item also bought the following items”). See also semi-supervised learning, supervised learning and reinforcement learning and training datasets.

This appears in the [https://www.designingbuildings.co.uk/wiki/Uk_government UK Government] website as '[https://post.parliament.uk/artificial-intelligence-ai-glossary/ Artificial intelligence (AI) glossary]' dated January 2024.

= Related articles on Designing for Buildings =

* AI building design tools
* Artificial intelligence and civil engineering.
* Artificial Intelligence and its impact on the project profession.
* Artificial intelligence and surveying.
* Artificial intelligence for smarter, safer buildings.
* Artificial intelligence in buildings.
* BSRIA publishes Artificial Intelligence in Buildings white paper.
* Building automation and control systems.
* Building information modelling.
* Computer aided design CAD.
* Computers in building design.
* Generative design.
* Global building automation.
* Internet of things.
* Parametric design.
* Predictive analytics.
* The impact of digital on civil engineering.
* The long expanding list of AI tools for building planning, design, construction and management.

Will AI ever be able to design buildings?

[[Category:DCN_Dataset]] [[Category:DCN_Definition]] [[Category:DCN_Software]] [[Category:Definitions]]