Representation Learning - Revision history

BPeat at 19:18, 16 September 2023

2023-09-16T19:18:38Z

BPeat at 19:16, 16 September 2023

2023-09-16T19:16:27Z

BPeat at 12:45, 16 January 2023

2023-01-16T12:45:44Z

BPeat at 11:50, 6 July 2020

2020-07-06T11:50:23Z

BPeat at 11:47, 6 July 2020

2020-07-06T11:47:36Z

BPeat at 11:39, 6 July 2020

2020-07-06T11:39:16Z

BPeat at 11:35, 6 July 2020

2020-07-06T11:35:05Z

BPeat at 11:34, 6 July 2020

2020-07-06T11:34:50Z

BPeat at 04:01, 3 February 2019

2019-02-03T04:01:00Z

BPeat: /* Large-Scale Graph */

2019-01-12T16:17:49Z

‎Large-Scale Graph

@@ Line 13: / Line 13: @@
 The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, [[Autoencoder (AE) / Encoder-Decoder | auto-encoders]], manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.  [http://arxiv.org/abs/1206.5538 Representation Learning: A Review and New Perspectives | Y. Bengio, A. Courville, and P. Vincent]
-* <b>Feature learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, [[Video|video]], and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]
+* <b>Feature Learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, [[Video|video]], and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]
-* <b>Manifold learning</b> is an approach to non-linear dimensionality reduction. Algorithms for this task are based on the idea that the dimensionality of many data sets is only artificially high. [http://scikit-learn.org/stable/modules/manifold.html#:~:text=Manifold%20learning%20is%20an%20approach,sets%20is%20only%20artificially%20high. Manifold learning | SciKitLearn]
+* <b>[[Manifold Hypothesis#Manifold Learning|Manifold Learning]]</b> is an approach to non-linear dimensionality reduction. Algorithms for this task are based on the idea that the dimensionality of many data sets is only artificially high. [http://scikit-learn.org/stable/modules/manifold.html#:~:text=Manifold%20learning%20is%20an%20approach,sets%20is%20only%20artificially%20high. Manifold learning | SciKitLearn]
 <youtube>e3GaXeqrG9I</youtube>

@@ Line 32: / Line 32: @@
 = Self-Supervised =
 <youtube>aGhYitrOJRc</youtube>
 = Semi-Supervised =
 <youtube>1tB7lALJ3ew</youtube>
 = Unsupervised =
 <youtube>y-SrsyckRbo</youtube>
 <youtube>ceD736_Fknc</youtube>

@@ Line 13: / Line 13: @@
 The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, [[Autoencoder (AE) / Encoder-Decoder | auto-encoders]], manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.  [http://arxiv.org/abs/1206.5538 Representation Learning: A Review and New Perspectives | Y. Bengio, A. Courville, and P. Vincent]
-* <b>Feature learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]
+* <b>Feature learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, [[Video|video]], and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]
 * <b>Manifold learning</b> is an approach to non-linear dimensionality reduction. Algorithms for this task are based on the idea that the dimensionality of many data sets is only artificially high. [http://scikit-learn.org/stable/modules/manifold.html#:~:text=Manifold%20learning%20is%20an%20approach,sets%20is%20only%20artificially%20high. Manifold learning | SciKitLearn]

@@ Line 11: / Line 11: @@
 * [[Feature Exploration/Learning]]
-The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.  [http://arxiv.org/abs/1206.5538 Representation Learning: A Review and New Perspectives | Y. Bengio, A. Courville, and P. Vincent]
+The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, [[Autoencoder (AE) / Encoder-Decoder | auto-encoders]], manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.  [http://arxiv.org/abs/1206.5538 Representation Learning: A Review and New Perspectives | Y. Bengio, A. Courville, and P. Vincent]
 * <b>Feature learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]

@@ Line 11: / Line 11: @@
 * [[Feature Exploration/Learning]]
-<b>Feature learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]
+The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.  [http://arxiv.org/abs/1206.5538 Representation Learning: A Review and New Perspectives | Y. Bengio, A. Courville, and P. Vincent]
 <youtube>e3GaXeqrG9I</youtube>

← Older revision		Revision as of 11:39, 6 July 2020
Line 9:		Line 9:

	* [[Reinforcement Learning (RL)]]		* [[Reinforcement Learning (RL)]]
		+	* [[Feature Exploration/Learning]]

	<b>Feature learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]		<b>Feature learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]

@@ Line 8: / Line 8: @@
 [http://www.google.com/search?q=Representation+Learning+deep+machine+learning+ML+artificial+intelligence ...Google search]
-* [Reinforcement Learning (RL)]]
+* [[Reinforcement Learning (RL)]]
 <b>Feature learning</b> or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. [http://en.wikipedia.org/wiki/Feature_learning Wikipedia]

@@ Line 7: / Line 7: @@
 [http://www.youtube.com/results?search_query=Representation+Learning YouTube search...]
 [http://www.google.com/search?q=Representation+Learning+deep+machine+learning+ML+artificial+intelligence ...Google search]
 <youtube>e3GaXeqrG9I</youtube>
 <youtube>Yr1mOzC93xs</youtube>
 == Representation Learning and Deep Learning ==

← Older revision		Revision as of 04:01, 3 February 2019
Line 1:		Line 1:
		+	{{#seo:
		+	\|title=PRIMO.ai
		+	\|titlemode=append
		+	\|keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS
		+	\|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
		+	}}
	[http://www.youtube.com/results?search_query=Representation+Learning YouTube search...]		[http://www.youtube.com/results?search_query=Representation+Learning YouTube search...]
		+	[http://www.google.com/search?q=Representation+Learning+deep+machine+learning+ML+artificial+intelligence ...Google search]

	<youtube>e3GaXeqrG9I</youtube>		<youtube>e3GaXeqrG9I</youtube>

← Older revision		Revision as of 16:17, 12 January 2019
Line 28:		Line 28:

	= Large-Scale Graph =		= Large-Scale Graph =
		+
		+	* [[Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning]]
		+
	<youtube>oQL4E1gK3VU</youtube>		<youtube>oQL4E1gK3VU</youtube>