Page 166 - Robotics and AI class 10
P. 166

The Problem Statement


        After filling the 4Ws problem canvas, you now need to summarise all the canvas into one template. The problem
        statement template helps us to put together all the key points into a single template for future reference. Problem
        statement template with space to fill details according to your goals:

            Our                                          [stakeholder(s)]                       Who








            has / have a problem that                 [issue, problem, need]                    What







            when / while                                [context, situation]                   Where







            An ideal solution would                [benefit of solution for them]               Why









                 Data Acquisition


        This is the second stage of the AI project cycle. It is the process of collecting data required for training the AI
        project. Data is raw information that is used to generate meaningful outcomes.
        If we have to make an artificial intelligence system to predict the traffic flow for a particular geographical location
        based on the previous traffic data. The data needs to be fed for the previous year into the system and the machine
        can be trained to use it to predict the traffic flow effectively. The previous year traffic flow data is known as the
        Training Data and the prediction it makes is using the Testing Data.
        The  efficiency  of  the  AI  system  is  dependent  on  the  authenticity  and  relevance  of  the  training  data.  Like  the
        previous topic discussed, if the traffic data is not for the same geo location or not for the same period last year, the
        predictability of the machine would not be accurate.

        Hence, for the AI system to be able to work efficiently, the authenticity and relevance of the training data to the
        scope of the problem statement is a must.


        Types of Data
        There are two types of data:
           • Training Data: It is data on which we train our AI project model. It is basically to fit the parameters of the project
          for the model. In training data, the output is available to the model.


              164     Touchpad Robotics & Artificial Intelligence-X
   161   162   163   164   165   166   167   168   169   170   171