Page 145 - Robotics and AI class 10
P. 145

3.  Define Machine learning.
   Ans.  Machine learning is a subset of AI which uses statistical methods to enable machines to improve decision making with   Unsolved Questions
 experience. It is one of the most popular techniques to build AI systems across the globe. It is the science of getting machines
 to interpret, process and analyse data in order to solve problems. It provides us statistical tools to explore the data.  SECTION A (Objective Type Questions)
                  uiz
 B.  Long answer type questions:
            A.  Tick ( ) the correct option.
    1.  Differentiate between Automatic Systems and Autonomous Systems.
   Ans.  Automatic Systems Automatic systems perform their tasks according to the predefined rules and are deterministic in   1.  ………………………. is the method of downloading information from the World Wide Web and storing it onto your computer
 nature, meaning that there is a defined problem with the defined steps to solve it. Example is Robotic Arms used to   for later reference.
 make cars in the Automobile Industry in the assembly line.  a.  Web Scraping      b.  Surveys
      Autonomous Systems Autonomous systems are non-deterministic in nature, meaning they do not have predefined   c.  Cameras      d.  Sensors
 tasks or defined steps to solve it, as they are trained to learn from their surroundings to act independently. Example is      2.  Which of the following is not a reliable source of data collection?
 Self Driven Car.  a.  Cameras                                       b.  Sensors
    2.  What are the steps involved in Machine learning?  c.  Web Scraping      d.  Letters
   Ans.  The Steps in Machine Learning are broadly categorised as follows:
               3.  When a machine possesses the ability to mimic the following human traits, it is said to have artificial intelligence.
      (i)  Data Collection: The data collection is the base in the process of Machine Learning.   Identify the positive traits that an AI machine should possess.

      (ii)   Data Preparation and Wrangling: The data collected needs to be prepared and made in a structured manner so    (i)  make decisions
 that the correlation between the variables and classes can be understood.    (ii)  bias
      (iii)   Model Selection: The Model Selection or Model Building is determined based on the outcome you want to achieve. It
 is a build using various analytical techniques of machine learning which are best suited for the task at hand.     (iii)  predict
                    (iv)  learn and improve on its own
      (iv)   Training the Model: In this process, we use the data prepared for Training and allow the Model Algorithm to
 process it and understand the patterns, features and rules, to be able to predict.   a. (i)  and (iii) only       b.  (i) , (iii) and (iv) only
      (v)   Testing,  Evaluating  and  Tuning  the  Model: The Testing data  is  used to check the accuracy  of the Models   c. (ii)  and (iv) only       d.  (i) ,(ii), and (iv) only
 prediction. The evaluation of the results and further Tuning of the algorithm helps the model to achieve complete      4.  The basis of decision making depends upon
 accuracy in predicting.   (i)  availability of information          (ii)  past experience
 (vi)  Deployment and Prediction: Once the model is tested, it is deployed in the real world.
                  (iii)  positive attitude                           (iv)  self-awareness
 C.  Competency-based/Application-based questions:   #Digital Literacy  a.  (i) and (ii)       b.  (ii) and (iv)
 1.  Assertion: Data plays a crucial role in AI projects as it serves as the foundation on which the AI model is built and   c.  (i), (ii) and (iv)       d.  (i), (ii) and iii)
 enables predictions and analysis.
               5.  Which of the the following defines the process of decision making?
 Reasoning: Data is a collection of raw information or facts that are processed to obtain meaningful information. It can   a.  Comparing our different alternatives      b.  Doing conclusions
 be in various forms, such as text, numbers, audio, and video clips. In AI projects, the model needs to be trained with a
 dataset to predict an output accurately, making data an essential part of the AI project.  c.  Looking for satisfactory options      d.  All of the above
     (i)  Both A and R are correct and R is the correct explanation of A.  B.  Fill in the blanks.
     (ii)  Both A and R are correct but R is NOT the correct explanation of A.
               1.  ………………………. is the science of getting machines to interpret, process and analyse data in order to solve problems.
     (iii)  A is correct but R is incorrect.
     (iv)  A is incorrect but R is correct.  2.  ………………………. processing can be used to teach machines to understand the nuances of human language.
   Ans.  (i)  Both A and R are correct and R is the correct explanation of A.     3.  Expand the term API. ………………………. .

 2.  Assertion: A machine is artificially intelligent when it can accomplish tasks by itself.  4.  ………………………. is a method of collecting data by watching facts as they occur.
 Reason: Humans become more and more intelligent with time as they gain experiences during their lives.     5.  Whenever we want the AI project to be able to predict an output, we need to ………………………. it with a data set first.
    (i)  Both A and R are correct and R is the correct explanation of A.
            C.  State whether these statements are true or false.
    (ii)  Both A and R are correct but R is NOT the correct explanation of A.
    (iii)  A is correct but R is incorrect.      1.  Decision making is not choosing from many alternatives.   ……….……
               2.  Extracting private data can be an offense.                                                ……….……
    (iv)  A is incorrect but R is correct.
   Ans.  (i)  Both A and R are correct and R is the correct explanation of A.     3.  In the data acquisition stage, it's very important that the data we provide to an AI project is big data.   ……….……

                                                                  Decision Making in Machines/Computers    143
   140   141   142   143   144   145   146   147   148   149   150