Page 31 - TP_Ai_Class_5
P. 31

Training Data

                 Training data is a collection of labelled information that is used to build a machine learning
                 model. It can be annotated text, images, videos or audios. Through training data, an AI
                 model learns to perform its task with high level of accuracy.


                 Test Data
                 The data that is given to an AI machine to test the machine is called test data. Based on

                 the training data the AI-enabled machine predicts the output from the test data.


                                Training  Data
                                                                        Prediction
                                                                                                 Video


                                           TXT
                                      TXT                                                   TXT  Text
                                                     Model Training

                                   Lables                                       TXT
                                                                         Test Data

                               Video  TXT  Audio
                                     Text




                 Pattern Recognition
                 Pattern recognition is a data analysis method that uses machine learning algorithms to
                 automatically recognise patterns and regularities in data. This data can be anything from

                 text and images to sounds or other definable qualities. Pattern recognition systems can
                 recognise familiar patterns quickly and accurately.































                                                                                       AI-Terminologies     29
   26   27   28   29   30   31   32   33   34   35   36