Types of Generative Models in Machine Learning
Generative Models in Machine Learning:
Generative Models are one of the most promising approaches towards this goal. To train a generative model we first collect a large amount of data in some domain and then train a model to generate data like it. Generative models are used in machine learning for either modeling data directly or as an intermediate step to forming a conditional probability density function.
A generative model is a model for generating all values for a phenomenon, both those that can be observed in the world and “target” variables that can only be computed from those observed. By contrast, discriminative models provide a model only for the target variables, generating them by analyzing the observed variables. In simple terms, discriminative models infer outputs based on inputs, while generative models generate both input and outputs typically given some hidden parameters.
Types of Generative Models:
1. Mixture Model: A mixture model is a probabilistic model for representing the presence of subpopulations within an overall population, without requiring that an observed data set should identify the subpopulation to which an individual observation belongs. Formally a mixture model corresponds to the mixture distribution that represents the probability distribution of observation in the overall population.
However, problems associated with “mixture distributions” relate to deriving the properties of the overall population from those of the sub-populations. Mixture models are used to make statistical inferences about the properties of the sub-populations given only observations on the pooled populations without sub-population identifying information.
2. Latent Variable Model: A latent variable model is a statistical model that relates a set of observable variables. An observable variable is also called a manifest variable, as opposed to a latent variable. It is a variable that can be observed and directly measured. Latent variable models are used in many disciplines, including psychology, demography, economics, engineering, medicine learning, artificial intelligence, bioinformatics, natural language processing, management, and the social sciences.
3. Gaussian Model: Gaussian model is a latent variable model that is also one of the most widely used models in machine learning. In a Gaussian model, each data point is a tuple (xi, zi) with xi.