Target Dataset

A Target Dataset is a dataset which elements are dependent variable values and that is an output data of a machine learning task.

• AKA: ML Output Dataset, Response Dataset, Outcome Dataset, Output Dataset, Dependent Dataset, Label Attribute Dataset.
• Example(s):
  • A labeled dataset which elemenents are target values and are used in a Supervised Machine Learning Task.
  • a Codomain.
  • …
• Counter-Example(s):
  • an unlabeled dataset for which there are no target values,
  • a Source Dataset,
  • Training Dataset,
  • Test Dataset,
  • Validation Dataset,
• See: Linear Regression, Machine Learning System, Artificial Neural Network Training System.

---

---

References

2018a

• (Wikipedia, 2018) ⇒ https://en.wikipedia.org/wiki/Dependent_and_independent_variables#Statistics Retrieved:2018-9-2.
  • In an experiment, a variable, manipulated by an experimenter, is called an independent variable (X); (Lane et al., 2018). The dependent variable (Y) is the event expected to change when the independent variable is manipulated (Random House Inc., 2001). In data mining tools (for multivariate statistics and machine learning), the dependent variable is assigned a role as target variable (or in some tools as label attribute), while an independent variable may be assigned a role as regular variable (Rapid-I GmbH, 2014). Known values for the target variable are provided for the training data set and test data set, but should be predicted for other data. The target variable is used in supervised learning algorithms but not in unsupervised learning.

2018b

• (Lane et al., 2018) ⇒ Independent and dependent variables: http://onlinestatbook.com/2/introduction/variables.html In: Online Statistics Education: A Multimedia Course of Study. Project Leader: David M. Lane, Rice University. Retrieved:2018-9-2.
  • QUOTE: Variables are properties or characteristics of some event, object, or person that can take on different values or amounts (as opposed to constants such as π that do not vary). When conducting research, experimenters often manipulate variables. For example, an experimenter might compare the effectiveness of four types of antidepressants. In this case, the variable is "type of antidepressant." When a variable is manipulated by an experimenter, it is called an independent variable. The experiment seeks to determine the effect of the independent variable on relief from depression. In this example, relief from depression is called a dependent variable. In general, the independent variable is manipulated by the experimenter and its effects on the dependent variable are measured.

2018c

• (ML Google Developers, 2018) ⇒ Google Developers (2018). "target". In: Machine Learning Glossary. Retrieved:2018-9-2.
  • QUOTE: Synonym for label.

2018d

• (ML Google Developers, 2018) ⇒ Google Developers. "label". In: Machine Learning Glossary. Retrieved:2018-9-2.
  • QUOTE: In supervised learning, the "answer" or "result" portion of an example. Each example in a labeled data set consists of one or more features and a label. For instance, in a housing data set, the features might include the number of bedrooms, the number of bathrooms, and the age of the house, while the label might be the house's price. In a spam detection dataset, the features might include the subject line, the sender, and the email message itself, while the label would probably be either "spam" or "not spam."

2018e

• (Wikipedia, 2018) ⇒ https://en.wikipedia.org/wiki/Codomain Retrieved:2018-9-2.
  • In mathematics, the codomain or target set of a function is the set into which all of the output of the function is constrained to fall. It is the set in the notation f: X → Y. The codomain is also sometimes referred to as the range but that term is ambiguous as it may also refer to the image.

    The codomain is part of a function if it is defined as described in 1954 by Nicolas Bourbaki, namely a triple (X, Y, F), with a functional subset of the Cartesian product X × Y and X is the set of first components of the pairs in (the domain). The set is called the graph of the function. The set of all elements of the form f(x), where ranges over the elements of the domain , is called the image of . In general, the image of a function is a subset of its codomain. Thus, it may not coincide with its codomain. Namely, a function that is not surjective has elements in its codomain for which the equation f(x) = y does not have a solution. An alternative definition of function by Bourbaki [Bourbaki, op. cit., p. 77], namely as just a functional graph, does not include a codomain and is also widely used. For example in set theory it is desirable to permit the domain of a function to be a proper class , in which case there is formally no such thing as a triple (X, Y, F). With such a definition functions do not have a codomain, although some authors still use it informally after introducing a function in the form f: X → Y.

2012

• (Wilson, 2012) ⇒ Bill Wilson (2012). "target ouput". In: The Machine Learning Dictionary for COMP9414
  • QUOTE: The target output of an artificial neuron is the output provided with the training pattern. The difference between this and the actual output of the neuron is the pattern error. This is used in .

2010

• (Rapid-I GmbH, 2014) ⇒ Rapid-I GmbH (2010) RapidMiner 5.0 Manual -English Version (PDF)
  • QUOTE: We therefore also call this special attribute label, since it sticks to your customers and identifies them like a brand label on a shirt or even a note on a pinboard. You will also find attributes which adopt this special role in RapidMiner under the name “label”. The goal of our efforts is to fill out this particular attribute for the total quantity of all customers. We will therefore also often speak of target attribute in this book instead of the term “label”. You will also frequently discover the term goal variable in the literature, which means the same thing.

2001

• (Random House Inc., 2001) ⇒ Random House Webster's Unabridged Dictionary. Random House, Inc. 2001. Page 534, 971. ISBN 0-375-42566-7.

---