Training a model

LeMarc

I have a general question. If i apply a supervised machine learning method one need to "train" the model to improve its accuracy. My question ist what exactly is meant by "training the model"? - To include more examples and modify the parameters of a model?

[Deleted User]

Hello @LeMarc,
The training data is an initial set of data used to help a program understand how to apply technologies like neural networks to learn and produce sophisticated results. It may be complemented by subsequent sets of data called validation and testing sets.

The process of modeling means training a machine learning algorithm to predict the labels from the features, tuning it for the business need, and validating it on holdout data. ... The output from modeling is a trained model that can be used for inference, making predictions on new data points.

Model: A machine learning model can be a mathematical representation of a real-world process. ... The learning algorithm finds patterns in the training data such that the input parameters correspond to the target. The output of the training process is a machine learning model which you can then use to make predictions.

A model parameter is a configuration variable that is internal to the model and whose value can be estimated from data. They are required by the model when making predictions. They values define the skill of the model on your problem. They are estimated or learned from data.


These are some good definitions from Google. If you search in Google you can find a lot of information.
Regards
mbs

[Deleted User]

Hello @LeMarc,
The training data is an initial set of data used to help a program understand how to apply technologies like neural networks to learn and produce sophisticated results. It may be complemented by subsequent sets of data called validation and testing sets.

The process of modeling means training a machine learning algorithm to predict the labels from the features, tuning it for the business need, and validating it on holdout data. ... The output from modeling is a trained model that can be used for inference, making predictions on new data points.

Model: A machine learning model can be a mathematical representation of a real-world process. ... The learning algorithm finds patterns in the training data such that the input parameters correspond to the target. The output of the training process is a machine learning model which you can then use to make predictions.

A model parameter is a configuration variable that is internal to the model and whose value can be estimated from data. They are required by the model when making predictions. They values define the skill of the model on your problem. They are estimated or learned from data.


These are some good definitions from Google. If you search in Google you can find a lot of information.
Regards
mbs

LeMarc

Thanks @mbs

that was quite helpful. Bear me with me, as Im a newbie to RM and ML as well.

[Deleted User]

@LeMarc

I am really happy to hear they help you Feel free when you have any question to call my ID. I will help you dear friend

Happy mining
mbs