Page 259 - AI Ver 1.0 Class 9
P. 259

2.  While training the AI model, Vinamra feeds in the images of water bottle with some ground rules to the model. The
                  model gets trained with these inputs and gives out answers in the form of predictions. This approach is commonly used
                  when we have a known dataset or labelled dataset. Identify this.
              Ans.  Rule Based Approach
               3.  Nishant was working  on stock market data.  He was assigned to keep  an  eye on the  share values of a particular
                  organization. While he was working on the project, he found that it is difficult to work on the data without using an AI
                  algorithm. Based on the above information, answer the following:

                  a. What kind of AI algorithm is best for handling his query and provides him with accurate results? Justify your answer.
                  b. How does an Artificial Neural Network work? Explain briefly.
              Ans.  a.   Artificial Neural Network is the best tool to work on stock market data. Neural networks are a series of algorithms
                    used to recognize hidden patterns in raw data, cluster and classify it, continuously learn and improve. They are used
                    in a variety of applications in stock markets, sales and marketing trends, risk assessment and fraud detection. The
                    main advantage is that the data features can be extracted automatically by the machine without the input from the
                    developer.
                  b.   A Neural Network is divided into multiple layers and each layer is further divided into several blocks called nodes.
                    Each node is responsible to do its task and pass on it to the next layer. First, we have the input layer which receives
                    the input in several different formats provided by the programmer and feeds it to the Neural Network.
                  No processing occurs in the input layer. The output layer predicts our final output. The output at each node is called
                  its activation or node value. The layer present in-between input and output layers is called the hidden layers which
                  perform most of the computations required by our network. These layers are not visible to the user. Each node of the
                  hidden layer has its own machine learning algorithm which it executes on the data received by the input layer. The
                  processed data is then fed to the subsequent hidden layer.
                  There can be multiple hidden layers depending upon the complexity of the function to be performed by the model.
                  The processed data by the hidden layers is passed onto the output layer which then gives the final output to the user.
                  No processing is done in the output layer.
               4.  Kalpesh is a botanist who is researching how temperature affects a particular culture of bacteria. While researching he
                  found that with the increase in temperature the bacterial growth steadily increases, then the growth plummets. Based
                  on this information answer the following questions:

                  a. Which AI model is best to represent this situation? Justify your answer.
                  b. Plot a graph to show the trend of this data.
              Ans.  a.   Regression model is the best AI model for this situation as it can generate the best mapping function to plot the
                    given parameters. Kalpesh found that the growth of the culture rises steadily based on temperature and then the
                    growth falls sharply. This shows that the graph will be a linear graph.
                  b.  Based on the information presented, the graph would look like:



                                                  Growth of the culture














                                                           Temperature



                                                                                     Neural Networks   257
   254   255   256   257   258   259   260   261   262   263   264