Page 205 - Ai_V1.0_Class9
P. 205

To produce fresh data, VAEs learn the distribution of the data and then sample from it.
                 Some of the examples of VAEs are as follows:

                    • It can generate new images like the
                   given  training  set.  For  instance,  a
                   VAE trained on images of faces can                             Latent Space
                   generate new, realistic-looking faces.
                    • It can produce new text that follows   Input  Encoder               Sample     Decoder           Output
                   the same style and structure as the                              Distribution
                   training  data,  assisting  writers with
                   drafts and ideas.

                    • It can be used for composing new
                   music pieces or  creating  sound
                   effects, music composition, etc.

                 Recurrent Neural Networks (RNNs)

                 RNNs are a special class of neural networks that excel at handling sequential data, like music or text. They excel
                 at tasks where the order of the data points is important, as they can remember previous inputs and use this
                 information to influence current outputs.

                 Some of the examples of RNNs are as follows:
                                                                                    Recurrence
                    • It can generate novel text in the style of
                   a specific author or genre, like creating
                   new  sentences  that  mimic  the  style  of
                   Shakespeare or generating dialogue for
                   a chatbot.
                    • It can predict the next character or word
                   in a sequence, like autocomplete features
                   in text editors and predictive text input
                   on smartphones.

                    • It can be used to predict future values
                   in a time series, such as stock prices or                                                 Output Layer
                   weather data, by learning patterns from   Input Layer
                   historical data.
                                                                                   Hidden Layer
                 Autoencoders (AEs)

                 These are neural networks that have been trained to
                 learn a compressed representation of data. They work
                 by  compressing  the  data  into  a  lower-dimensional
                 form (encoding) and then decompressing it back to      Input   Encoder         Latent Space  Decoder  Output
                 its  original  form  (decoding).  This  process  helps  the
                 network  learn  the  most  important  features  of  the
                 data.



                                                                                  Introduction to Generative AI  203
   200   201   202   203   204   205   206   207   208   209   210