Page 201 - Ai_V1.0_Class9
P. 201

Unsupervised Learning and Generative Modelling

                 Unsupervised learning is a type of machine learning where models are trained using data that does not have
                 labels. This means the model has to find patterns and relationships in the data on its own. Generative modelling
                 is a specific approach within unsupervised learning that focuses on understanding and modelling how the data
                 is generated. Generative models try to learn the underlying rules that produce the data, so they can create new
                 examples that look similar to the original data. In summary, Unsupervised learning is about finding patterns in
                 unlabelled data, and generative modelling is a method within this type of learning that aims to understand and
                 replicate how the data is made.


                 Unsupervised Learning

                                                                       Output
                                    Input                                                     Example that's similar to
                       Unstructured/Unlabelled dataset        Emergent pattern/inherent        what's in the dataset
                                                                       structure



















                 The goal of unsupervised learning is to find patterns, structures, or representations in the data without human
                 intervention. An unsupervised learning approach works on an unlabelled dataset. This means that the data
                 which is fed to the machine is random and there is no know-how available about it to the trainer.


                 Generative Modelling
                 Generative Modelling do not necessarily require labelled datasets. It can work with unlabelled data to learn the
                 underlying distribution of the data and can generate structured data from the random noise dataset. So, if
                 random images are fed as training data for the model it can create relevant output based on the features of the
                 input data. If there are random images which depict streets, cars, buildings, sky, etc. In a given dataset of street
                 images, a Generative Modelling can learn to generate new street scenes that look like the ones in the dataset. In
                 another example, if given a dataset of news articles, a generative model can learn to generate new articles that
                 resemble the style and content of the training data. Let us take an example.

                 The following images are given as input to the Generative AI model:
















                                                                                  Introduction to Generative AI  199
   196   197   198   199   200   201   202   203   204   205   206