Page 158 - AI Ver 1.0 Class 10
P. 158

Stage 4: Data Modelling

              An  important  stage  in  the  process  of  AI  project  cycle  where  we  decide  on  the  technique  to  be  followed  for
              building a model from the prepared data. It is a mathematical approach in which an algorithm is designed as
              per the requirement of the system which is ready to be installed to analyse the data technically. In the previous
              stage of data exploration, we used the graphical representation of data to make it easy to understand the trends
              and patterns. But when it comes to machines, it only understands the language of 1s and 0s so they only rely on
              mathematical representation of data.


                                                                                          Machine
                                                                                         Learning
                                                               Learning
                                                                Based
                                    AI Models                                              Deep
                                                                                         Learning
                                                              Rule Based



              AI modelling techniques can be broadly classified into the following 2 approaches:


              Rule Based Approach
              This approach is based on a set of rules and facts defined by the developer and fed to the machine to perform
              its task accordingly to generate the desired output. These models can operate with simple basic information
              and data.
              To explain it further, let's take an example. If you have a dataset that consists of weather conditions, a basis which
              we can predict if the lion would be visible on a specific Safari Day to the tourists. The parameters can be cloud
              cover, temperature, wind speed, humidity. When these parameters are recorded and fed in the machine giving
              the favourable combinations when the Lion would be visible and rest can be considered that the lion would not
              be visible. Now, to test the model, the machine is given a scenario of the cloud cover, temperature, wind speed,
              humidity. The model will compare the same with the fed in the dataset and if there is a match, would let know if
              the lion would be visible or not. This is called a rule-based approach.
              The drawback of this approach is that the learning for the machine is static, as once trained, the machine does not
              take into consideration any changes made in the original training dataset. If the machine is tested on a different
              dataset from the rules and the data fed in at the training stage, the machine will fail and will not learn from the
              new conditions encountered.


              Learning Based Approach

              This  approach  refers  to  the  model  where  the  relationship  or  patterns  in  the  data  are  not  defined  by  the
              developer. Random data is fed into the machine and the machine develops its own pattern or trends based
              on data outputs.
              This approach is considered to take care of the challenges of rule-based systems.
              For example, suppose you have a dataset of 1000 images of flowers.  Now you do not have any clue as to what
              trend is being followed in this dataset as you don’t know their names, colour or any other feature. Thus, you would
              put this into a learning approach-based AI machine and the machine would come up with various patterns it has
              observed in the features of these 1000 images.
              It might cluster the data on the basis of colour , size, shape, etc. It might also come up with some very unusual
              clustering algorithm which you might not have even thought of!
              The Learning Based Approach can further be divided into three sections:






                        156   Touchpad Artificial Intelligence-X
   153   154   155   156   157   158   159   160   161   162   163