DEV Community

Cover image for 10 Important Machine Learning Terminologies you should always keep in mind
Favor Onuoha
Favor Onuoha

Posted on • Updated on

10 Important Machine Learning Terminologies you should always keep in mind

It is my strong believe that the key to understanding ML is knowing its terminologies and also knowing what you are doing.

You will love the last one πŸ”₯πŸ”₯πŸ”₯

1) Epoch

A full training pass over the entire dataset such that each example has been seen once. Thus, an epoch represents N/batch size training iterations, where N is the total number of examples.

2) Example

One row of a dataset. An example contains one or more features and possibly a label. See also labeled example and unlabeled example.

3) Label

It is the result portion of an example. Each example in a dataset consists of one or more features and a label.

In a spam detection dataset, the features may include the subject, sender, and the message, while the label would probably be either "spam" or "not spam."

4) Learning Rate

A scalar used to train a model via gradient descent. During each iteration, the gradient descent algorithm multiplies the learning rate by the gradient. The resulting product is called the gradient step.

5) Model

The representation of what a machine learning system has learned from the training data.

6) Training

The process of determining the ideal parameters comprising a model.

7) Stochastic Gradient Descent (SGD)

A gradient descent algorithm in which the batch size is one. In other words, SGD relies on a single example chosen uniformly at random from a dataset to calculate an estimate of the gradient at each step.

8) Squared Loss (L2 Loss)

This function calculates the squares of the difference between a model's predicted value for a labeled example and the actual value of the label.

Due to squaring, this loss function amplifies the influence of bad predictions.

9) Loss

A measure of how far a model's predictions are from its label. Or, to phrase it more pessimistically, a measure of how bad the model is. To determine this value, a model must define a loss function.

10) Machine Learning

Some novices don't know the meaning of this term. However, they aren't to blame as to most of them simply get straight to coding and not learning the basics.

Machine Learning is a program or system that builds (trains) a predictive model from input data.

The system uses the learned model to make useful predictions from new (never-before-seen) data drawn from the same distribution as the one used to train the model.

Machine learning also refers to the field of study concerned with these programs or systems.

Conclusion

Thank you for reading πŸ”₯πŸ”₯πŸ”₯, and I hope you found this article useful πŸ”₯

If you enjoyed reading, please consider following me here on Dev.to and also on Twitter @ heyOnuoha so you don’t miss out on new content on topics like:

  • Web Development (JS and Python)
  • Improving as a developer
  • Machine Learning

Support Me :

πŸ‘‰ Follow Me on Twitter
πŸ‘‰ Buy me a β˜•
Buy Me A Coffee

Cheers!!!

Discussion (0)