Jupyter notebook

A Jupyter Notebook is an interactive document produced by Jupyter which contains both computer code (e.g. Python) and rich text elements (paragraph, equations, figures, links, etc...). A new notebook can be initiated by running jupyter notebook in a terminal, which will launch the notebook in your web browser. A Notebook document is both human-readable containing the analysis description and the results (figures, tables, etc..) as well as executable which can be run to perform data analysis.

Landmark Points

A deformable object is represented with a set of semantically meaningful points that correspond to its distinctive parts. These points are commonly referred to as landmark points.

In-The-Wild

The term "in-the-wild images" (or data in general) is used in order to describe images that are captured under totally unconstrained conditions. Such images can be easily acquired using online search engines. In-the-wild databases are a determinative factor towards creating powerful generic deformable models.

Deformable Models

Deformable models are a family of methodologies that aim to model the shape and appearance variations of a deformable object class.

Generative Model

A generative model is a model for randomly generating observable data values, typically given some hidden parameters. It specifies a joint probability distribution over observation and label sequences. Generative models are used in machine learning for either modeling data directly (i.e., modeling observations drawn from a probability density function), or as an intermediate step to forming a conditional probability density function. Generative models contrast with discriminative models, in that a generative model is a full probabilistic model of all variables, whereas a discriminative model provides a model only for the target variable(s) conditional on the observed variables.

Discriminative Model

Discriminative models are a class of models used in machine learning for modeling the dependence of an unobserved variable y on an observed variable x. Within a probabilistic framework, this is done by modeling the conditional probability distribution P(y|x), which can be used for predicting y from x. Discriminative models, as opposed to generative models, do not allow one to generate samples from the joint distribution of x and y.

results matching ""

    No results matching ""