Data Science: Training (Definitions)

"A step by step procedure for adjusting the weights in a neural net." (Laurene V Fausett, "Fundamentals of Neural Networks: Architectures, Algorithms, and Applications", 1994)

[supervised training:] "Process of adjusting the weights in a neural net using a learning algorithm; the desired output for each of a set of training input vectors is presented to the net. Many iterations through the training data may be required." (Laurene V Fausett, "Fundamentals of Neural Networks: Architectures, Algorithms, and Applications", 1994)

[unsupervised training:] "A training procedure in which only input vectors x are supplied to a neural network; the network learns some internal features of the whole set of all the input vectors presented to it." (Nikola K Kasabov, "Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering", 1996)

"The process of adjusting the connection weights in a neural network under the control of a learning algorithm." (Joseph P Bigus, "Data Mining with Neural Networks: Solving Business Problems from Application Development to Decision Support", 1996)

[supervised training:] "Training of a neural network when the training examples comprise input vectors x and the desired output vectors y; training is performed until the neural network 'learns' to associate each input vector x with its corresponding and desired output vector y." (Nikola K Kasabov, "Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering", 1996)

"Exposing a neural computing system to a set of example stimuli to achieve a particular user-defined goal." (Guido J Deboeck and Teuvo Kohonen, "Visual explorations in finance with self-organizing maps", 2000)

"The process used to configure an artificial neural network by repeatedly exposing it to sample data. In feed-forward networks, as each incoming vector or individual input is processed, the network produces an output for that case. With each pass of every case vector in a sample (see epoch), connection weights between neurons are modified. A typical training regime may require tens to thousands of complete epochs before the network converges (see convergence)." (David Scarborough & Mark J Somers, "Neural Networks in Organizational Research: Applying Pattern Recognition to the Analysis of Organizational Behavior", 2006)

"The process a data mining model uses to estimate model parameters by evaluating a set of known and predictable data." (Microsoft, "SQL Server 2012 Glossary", 2012)

"In data mining, the process of fitting a model to data. This is an iterative process and may involve thousands of iterations or more." (Meta S Brown, "Data Mining For Dummies", 2014)

"The process of adjusting the weights and threshold values in a neural net to get a desired outcome" (Nell Dale & John Lewis, "Computer Science Illuminated" 6th Ed., 2015)

"Model training is the process of fitting a model to data." (Alex Thomas, "Natural Language Processing with Spark NLP", 2020)

"Model Training is how artificial intelligence (AI) is taught to perform its tasks, and in many ways follows the same process that new human recruits must also undergo. AI training data needs to be unbiased and comprehensive to ensure that the AI’s actions and decisions do not unintentionally disadvantage a set of people. A key feature of responsible AI is the ability to demonstrate how an AI has been trained." (Accenture)