Machine learning - Revision history

Vipul: /* Classification based on nature of training data */

2021-06-12T01:49:06Z

Classification based on nature of training data

← Older revision		Revision as of 01:49, 12 June 2021
Line 18:		Line 18:
	\| [[supervised learning]] \|\| Explicit training data (input-output pairs) are provided. These can be used to learn the parameters for the functional form that can then be used to make predictions.		\| [[supervised learning]] \|\| Explicit training data (input-output pairs) are provided. These can be used to learn the parameters for the functional form that can then be used to make predictions.
	\|-		\|-
	\| [[unsupervised learning]] \|\| The training data as provided does not provide explicit outputs for explicit inputs. For instance, in the context of classification problems, an unsupervised learning problem would simply provide a lot of inputs without specifying the output values for those inputs. The job of the machine learning algorithm is to use the distribution of the inputs to figure out the output values.		\| [[unsupervised learning]] \|\| The training data as provided includes a list of inputs but does not provide explicit outputs for explicit inputs. For instance, in the context of classification problems, an unsupervised learning problem would simply provide a lot of inputs without specifying the output values for those inputs. The job of the machine learning algorithm is to use the distribution of the inputs to figure out the output values.
	\|-		\|-
	\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.		\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.

Vipul: /* The case of learning a function */

2021-06-12T01:48:36Z

The case of learning a function

← Older revision		Revision as of 01:48, 12 June 2021
Line 7:		Line 7:
	Although this particular formulation is not the most natural formulation of all machine learning problems, any machine learning problem can be converted to this formulation.		Although this particular formulation is not the most natural formulation of all machine learning problems, any machine learning problem can be converted to this formulation.

	An output function depends on some inputs (called [[feature]]s) (and possibly a random noise component). We have access to some training data where we have the value of the output function, and we either already have or can get the values of the features. The machine learning problem asks for an explicit description of a function that would perform well on new inputs that we provide to it.		An output function depends on some inputs (called [[feature]]s) (and possibly a random noise component). We have access to some training data, or thee ability to explore and discover training data, where we may or may not have the value of the output function, and we either already have or can get the values of the features. The machine learning problem asks for an explicit description of a function that would perform well on new inputs that we provide to it.

	==Types of machine learning==		==Types of machine learning==

IssaRice: /* Classification based on nature of training data */

2020-03-23T23:28:49Z

Classification based on nature of training data

← Older revision		Revision as of 23:28, 23 March 2020
Line 22:		Line 22:
	\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.		\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.
	\|-		\|-
	\| [[reinforcement learning]] \|\| Unlike supervised learning, the training data is not chosen by the user; instead, the agent being trained generates the training data by interacting with the environment. In addition, the kind of feedback is different: in supervised learning the feedback is ''instructive'' (i.e. does not depend on the ~~input~~ the system selects), but in reinforcement learning the feedback is ''evaluative'' (i.e. depends on the action selected by the agent).<ref>Sutton and Barto. ''Reinforcement Learning: An Introduction'' (2nd ed). p. 25.</ref><ref>[https://www.coursera.org/learn/fundamentals-of-reinforcement-learning/lecture/PtVBs/sequential-decision-making-with-evaluative-feedback "Sequential Decision Making with Evaluative Feedback"]. Coursera.</ref>		\| [[reinforcement learning]] \|\| Unlike supervised learning, the training data is not chosen by the user; instead, the agent being trained generates the training data by interacting with the environment. In addition, the kind of feedback is different: in supervised learning the feedback is ''instructive'' (i.e. does not depend on the outputs the system selects), but in reinforcement learning the feedback is ''evaluative'' (i.e. depends on the action selected by the agent).<ref>Sutton and Barto. ''Reinforcement Learning: An Introduction'' (2nd ed). p. 25.</ref><ref>[https://www.coursera.org/learn/fundamentals-of-reinforcement-learning/lecture/PtVBs/sequential-decision-making-with-evaluative-feedback "Sequential Decision Making with Evaluative Feedback"]. Coursera.</ref>
	\|}		\|}

IssaRice at 23:27, 23 March 2020

2020-03-23T23:27:22Z

← Older revision		Revision as of 23:27, 23 March 2020
Line 48:		Line 48:
	\| [[online learning]] \|\| Here, the input data is streamed to the algorithm, one instance at a time. For the one-instance case (each data point) three steps occur: (a) The algorithm reads the data (the input only), (b) the algorithm makes a prediction of the output, (c) the algorithm learns the actual output and updates the parameters according to that.		\| [[online learning]] \|\| Here, the input data is streamed to the algorithm, one instance at a time. For the one-instance case (each data point) three steps occur: (a) The algorithm reads the data (the input only), (b) the algorithm makes a prediction of the output, (c) the algorithm learns the actual output and updates the parameters according to that.
	\|}		\|}

			==References==

			<references/>

IssaRice: /* Classification based on nature of training data */

2020-03-23T23:26:45Z

Classification based on nature of training data

← Older revision		Revision as of 23:26, 23 March 2020
Line 22:		Line 22:
	\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.		\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.
	\|-		\|-
	\| [[reinforcement learning]] \|\|		\| [[reinforcement learning]] \|\| Unlike supervised learning, the training data is not chosen by the user; instead, the agent being trained generates the training data by interacting with the environment. In addition, the kind of feedback is different: in supervised learning the feedback is ''instructive'' (i.e. does not depend on the input the system selects), but in reinforcement learning the feedback is ''evaluative'' (i.e. depends on the action selected by the agent).<ref>Sutton and Barto. ''Reinforcement Learning: An Introduction'' (2nd ed). p. 25.</ref><ref>[https://www.coursera.org/learn/fundamentals-of-reinforcement-learning/lecture/PtVBs/sequential-decision-making-with-evaluative-feedback "Sequential Decision Making with Evaluative Feedback"]. Coursera.</ref>
	\|}		\|}

Sebastian at 22:04, 9 February 2020

2020-02-09T22:04:57Z

← Older revision		Revision as of 22:04, 9 February 2020
Line 1:		Line 1:
	==Definition==		==Definition==

	'''Machine learning''' can be defined as the problem of using partial data about a function or relation to make predictions about how the function or relation would perform on new data.		'''Machine learning''' can be defined as the problem of using partial data about a function or relation to make predictions about how the function or relation would perform on new data. It is the branch of AI that covers its statistical part.

	===The case of learning a function===		===The case of learning a function===

Vipul: /* Classification based on nature of training data */

2014-07-26T02:10:05Z

Classification based on nature of training data

← Older revision		Revision as of 02:10, 26 July 2014
Line 21:		Line 21:
	\|-		\|-
	\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.		\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.
			\|-
			\| [[reinforcement learning]] \|\|
	\|}		\|}

Vipul at 02:09, 26 July 2014

2014-07-26T02:09:03Z

← Older revision		Revision as of 02:09, 26 July 2014
Line 9:		Line 9:
	An output function depends on some inputs (called [[feature]]s) (and possibly a random noise component). We have access to some training data where we have the value of the output function, and we either already have or can get the values of the features. The machine learning problem asks for an explicit description of a function that would perform well on new inputs that we provide to it.		An output function depends on some inputs (called [[feature]]s) (and possibly a random noise component). We have access to some training data where we have the value of the output function, and we either already have or can get the values of the features. The machine learning problem asks for an explicit description of a function that would perform well on new inputs that we provide to it.

	==~~Aspects~~ of machine learning==		==Types of machine learning==

			===Classification based on nature of training data===

			{\| class="sortable" border="1"
			! Type of machine learning !! Description
			\|-
			\| [[supervised learning]] \|\| Explicit training data (input-output pairs) are provided. These can be used to learn the parameters for the functional form that can then be used to make predictions.
			\|-
			\| [[unsupervised learning]] \|\| The training data as provided does not provide explicit outputs for explicit inputs. For instance, in the context of classification problems, an unsupervised learning problem would simply provide a lot of inputs without specifying the output values for those inputs. The job of the machine learning algorithm is to use the distribution of the inputs to figure out the output values.
			\|-
			\| [[semi-supervised learning]] \|\| The training data is a mix of explicit input-output pairs and input-only data. Semi-supervised learning combines some of the aspects of supervised learning and unsupervised learning.
			\|}

			===Classification based on nature of prediction===

	{\| class="sortable" border="1"		{\| class="sortable" border="1"
	! ~~Aspect !! What gets chosen here~~ !! Description		! Type of prediction problem !! Description
	\|-		\|-
	\| ~~[[Feature selection]] \|\| The set of features that the model depends on.~~ \|\| ~~Based on the problem domain~~, ~~we come up with a list of relevant features that affect~~ the output ~~function~~. ~~If we choose too few features~~, ~~then~~ the ~~task might~~ be ~~theoretically impossible. For instance, if the only feature we have for~~ a ~~house is its area, and we need to predict the price, we cannot do the~~ prediction ~~too well~~. ~~The more the features, the better our ability to predict in principle. However, too many features means more effort spent collecting their values, and there are also dangers of~~ [[~~overfitting~~]].		\| binary classification problem \|\| Here, the output has only two permissible values. Therefore, the prediction problem can be viewed as a yes/no or a true/false prediction problem. Models for binary classification can be probabilistic (such as [[logistic regression]] or [[artificial neural network]]s) or yes/no (such as [[support vector machine]]s). Note that probabilistic binary classification models structurally resemble regression models.
	\|-		\|-
	\| ~~[[Model selection]] (not to be confused with [[hyperparameter optimization]])~~ \|\| ~~The functional form (with [[parameter]]s) describing how~~ the output ~~depends on the features~~. ~~\|\| This again depends on theoretical knowledge based on the~~ problem ~~domain, as well as empirical exploration~~ of ~~the data gathered~~.		\| discrete variable prediction problem, or multi-class classification problem \|\| Here, the output can take one of a finite number of values. We can also think of this as a classification problem where each input case needs to be sorted into one of finitely many classes.
	\|-		\|-
	\| ~~[[Cost function selection]] \|\| The cost function (~~or ~~error function) used to measure error on new data.~~ \|\| ~~This again depends on theoretical knowledge based on the problem domain~~, ~~and also on~~ the ~~choice~~ of ~~model~~. ~~Often,~~ the ~~error function selection is bundled with the model selection, because part~~ of ~~the model selection process also includes identifying the nature~~ of distribution of errors or anomalies. This has the properly that if we choose parameters so that our predicted function matches the actual function precisely, the error is zero. In principle, however, the error function is independent of the model, so we can essentially combine any permissible model with any permissible error function.		\| regression problem, or continuous variable prediction problem \|\| Here, the output can take a value over a continuous range of values.
			\|}

			===Classification based on the stage of learning===

			{\| class="sortable" border="1"
			! Stage of learning !! Description
	\|-		\|-
	\| ~~Regularization-type choices~~ \|\| ~~The choice~~ of ~~regularization~~ function to ~~add to~~ the ~~cost function when using on~~ the training data. ~~Requires choosing [[regularization hyperparameter]](s)~~. \|\|		\| [[eager learning]] \|\| This is the more common form of learning. Here, the training data is pre-processed and an explicit and compact representation of the function is learned from it (usually, in the form of a paramater vector). The learning phase that uses the training data to learn the compact representation takes substantially greater time, but once this phase is done, the training data can be thrown away. The compact representation takes much less memory than the training data and can be used to quickly compute the output for any input.
	\|-		\|-
	\| [[~~Learning algorithm~~]] ~~applied on the training data~~ \|\| ~~The values~~ of the ~~parameters (~~not ~~uniquely determined, we might get~~ a ~~portfolio of choices for different hyperparameter choices)\|\| This is the algorithm that tries~~ to ~~solve~~ the ~~optimization function of choosing values of the parameters (for our chosen model) so that the error function~~ is ~~minimized (or close~~ to ~~minimized)~~. ~~Note that we~~ are ~~trying to minimize~~ the ~~error~~ function ~~for unknown inputs, but our algorithm~~ is ~~being trained~~ on ~~known inputs. Thus, there are issues of [[overfitting]]. This problem is addressed through a number of techniques, including [[regularization]] and [[early stopping]]~~.		\| [[lazy learning]] \|\| With this form of learning, the training data is not completely pre-processed. Every time a new prediction needs to be made, the training data is used to make the prediction. Lazy learning algorithms are useful in cases where the prediction of function values is based on nearby values.
	\|-		\|-
	\| [[~~Cross-validation~~]] (~~relates to hyperparameter optimization~~) \|\| The ~~actual values of~~ the ~~hyperparameters and parameters \|\| This includes techniques that tweak~~ the ~~[[hyperparameter]]s that control~~ the ~~performance~~ of the ~~learning~~ algorithm~~. These could include learning rate parameters for gradient descent, or regularization~~ parameters ~~introduced~~ to ~~avoid overfitting~~.		\| [[online learning]] \|\| Here, the input data is streamed to the algorithm, one instance at a time. For the one-instance case (each data point) three steps occur: (a) The algorithm reads the data (the input only), (b) the algorithm makes a prediction of the output, (c) the algorithm learns the actual output and updates the parameters according to that.
	\|}		\|}

Vipul: /* Aspects of machine learning */

2014-06-07T16:25:06Z

Aspects of machine learning

← Older revision		Revision as of 16:25, 7 June 2014
Line 22:		Line 22:
	\| Regularization-type choices \|\| The choice of regularization function to add to the cost function when using on the training data. Requires choosing [[regularization hyperparameter]](s). \|\|		\| Regularization-type choices \|\| The choice of regularization function to add to the cost function when using on the training data. Requires choosing [[regularization hyperparameter]](s). \|\|
	\|-		\|-
	\| [[Learning algorithm]] \|\| ~~Nothing~~ \|\| This is the algorithm that tries to solve the optimization function of choosing values of the parameters (for our chosen model) so that the error function is minimized (or close to minimized). Note that we are trying to minimize the error function for unknown inputs, but our algorithm is being trained on known inputs. Thus, there are issues of [[overfitting]]. This problem is addressed through a number of techniques, including [[regularization]] and [[early stopping]].		\| [[Learning algorithm]] applied on the training data \|\| The values of the parameters (not uniquely determined, we might get a portfolio of choices for different hyperparameter choices)\|\| This is the algorithm that tries to solve the optimization function of choosing values of the parameters (for our chosen model) so that the error function is minimized (or close to minimized). Note that we are trying to minimize the error function for unknown inputs, but our algorithm is being trained on known inputs. Thus, there are issues of [[overfitting]]. This problem is addressed through a number of techniques, including [[regularization]] and [[early stopping]].
	\|-		\|-
	\| [[~~Hyperparameter optimization~~]] ~~for learning algorithm~~ \|\| The actual values of the hyperparameters and parameters \|\| This includes techniques that tweak the [[hyperparameter]]s that control the performance of the learning algorithm. These could include learning rate parameters for gradient descent, or regularization parameters introduced to avoid overfitting.		\| [[Cross-validation]] (relates to hyperparameter optimization) \|\| The actual values of the hyperparameters and parameters \|\| This includes techniques that tweak the [[hyperparameter]]s that control the performance of the learning algorithm. These could include learning rate parameters for gradient descent, or regularization parameters introduced to avoid overfitting.
	\|}		\|}

Vipul: /* Aspects of machine learning */

2014-06-07T16:22:10Z

Aspects of machine learning

← Older revision		Revision as of 16:22, 7 June 2014
Line 22:		Line 22:
	\| Regularization-type choices \|\| The choice of regularization function to add to the cost function when using on the training data. Requires choosing [[regularization hyperparameter]](s). \|\|		\| Regularization-type choices \|\| The choice of regularization function to add to the cost function when using on the training data. Requires choosing [[regularization hyperparameter]](s). \|\|
	\|-		\|-
	\| [[Learning algorithm]] \|\| This is the algorithm that tries to solve the optimization function of choosing values of the parameters (for our chosen model) so that the error function is minimized (or close to minimized). Note that we are trying to minimize the error function for unknown inputs, but our algorithm is being trained on known inputs. Thus, there are issues of [[overfitting]]. This problem is addressed through a number of techniques, including [[regularization]] and [[early stopping]].		\| [[Learning algorithm]] \|\| Nothing \|\| This is the algorithm that tries to solve the optimization function of choosing values of the parameters (for our chosen model) so that the error function is minimized (or close to minimized). Note that we are trying to minimize the error function for unknown inputs, but our algorithm is being trained on known inputs. Thus, there are issues of [[overfitting]]. This problem is addressed through a number of techniques, including [[regularization]] and [[early stopping]].
	\|-		\|-
	\| [[Hyperparameter optimization]] for learning algorithm \|\| This includes techniques that tweak the [[hyperparameter]]s that control the performance of the learning algorithm. These could include learning rate parameters for gradient descent, or regularization parameters introduced to avoid overfitting.		\| [[Hyperparameter optimization]] for learning algorithm \|\| The actual values of the hyperparameters and parameters \|\| This includes techniques that tweak the [[hyperparameter]]s that control the performance of the learning algorithm. These could include learning rate parameters for gradient descent, or regularization parameters introduced to avoid overfitting.
	\|}		\|}