Supported techniques

Firenze supports different techniques for training models.

If your desired technique is not present, please submit a feature request.

Tabular classification

A type of machine learning where the input data is organised in a table or spreadsheet format, with rows representing individual samples and columns representing features of those samples. The goal is to predict a categorical label for each row based on the values in the columns.

Tabular regression

A type of machine learning where the input data is organised in a table or spreadsheet format, with rows representing individual samples and columns representing features of those samples. The goal is to predict a numerical value for each row based on the values in the columns.

Text classification

A type of machine learning that involves analysing and categorising text data, such as emails, news articles, or social media posts. The goal is to assign a label or category to each piece of text based on its content. Text classification has two sub-types, single label and multi label output. The single label provides one label or category to each piece of text, while multi label can provide one or more labels or categories.

Image classification

A type of machine learning that involves analysing and categorising image data. The goal is to assign a label or category to each image.

Named entity recognition

A technique in natural language processing that involves identifying and extracting specific information, such as the names of people, organisations, and locations, from unstructured text data.

Relationship extraction

A technique in natural language processing that involves identifying relationships between entities mentioned in text, such as the relationship between two people or an organisation and a location.

Text captioning

A technique in natural language processing that generates a brief summary or caption that describes the content of an image or video.