Previous Years’ Questions @ 1. During Data Acquisition, feeding previous data into the machine is called a. Training Data CO _ >. Predicting Data Testing Data O d. Evaluating Data Ans. a. Training Data 2. Which of the following is the correct feature of Neural network? a. It can improve the efficiency of two models. b. It is useful with small dataset. . They are modelled on humanis brains and nervous system. 4d. They need human intervention. Ans. c. They are modelled on humans brains and nervous system. 2. 180 | Touchpad Artificial Intelligence (Ver, 2.0)-X \_UAAAD \ (2023, (2023) CO0OOi 4, tis learing model the dataset tie “ is fed to the ‘machine is labelled. Name the model. . «supervised Learning problem Canvas i isa par 4 as Part of: (2023) problem Scoping ° O O b. Data Acquisition «, Modeling © 4 ratuation O nea, Problem Scoping rtrefers to the unsupervised learning algorithm whi ee aa '9 algorithm which can cluster the unknown data according Leni taae a. Regression Ob cessation ° Clustering d. Dimensionalit duction ns. clustering . — - Id make von One | i looks at various parameters which affect the problem we wish to solve, as this woul (2023) 6. Under many lives better. ‘ans. Problem Scoping 7, Regression is one of the type of supervised learni i ; f ing mod not to be continuous. (True / False) 1g model, where data is classified according to label: \s and data need (2023) ns. False What is dimensionality reduction? Zs, Dimensionality reduction refers to reducing the dimensions of objects and stil being ble to make sense out of the data. Itreduces the dimension without losing any information in dimensionality reduction. Oy is the significance of the Al project cycle? Also, explain in detail About how Data Acquistion is different from data Arploration. (2023) ns The Al Project Cycle provides us with an appropriate framework which can lead us towards the goal. Th [2023] 1 Al Project. Cycle mainly has 5 stages: 1. Problem Scoping 2, Data Acquisition 3. Data Exploration 4, Modelling Data Acquisi It is a process of acquiring data web scraping, sensors, cameras, observation, and API into the model is training data and prediction data is testing data, ted may be complex. So data exploration is used to make some Here the data will be represented through various graphs and 5, Evaluation from various sources, Data can be collected through surveys, interviews, programs. Data collected before data collection. The data which is fed Data Exploration: In data acquisition data which are collect pattern from data or visualize the data in a proper format. Visualization forms. 10, Assertion (A): The training data should be authentic and relevant to the problem statement scoped. (2022) Reason (R): It increases the Al Project efficiency. 1d Reason (R) are correct and Reason (R) is the correct explanation of Assertion (A). a. Both Assertion (A) an ». Both Assertion (A) and & Assertion (A) is correct, but Reason (R) is not correct. . Assertion (A) is not correct, but Reason (R) is correct. Ans. a. Both Assertion (A) and Reason (R) are correct and Reason (R) is the correct explanation of Assertion Reason (R) are correct, but Reason (R) is not the correct explanation of Assertion (A). O O Oo Oo A. arProject Cycle | 181 {LMTf AAA involves colle a from various authentic sources such as reliable websites, vari A ting data fro observations, surveys Cb: bata Evaluation Ry a. Data Acquisition O © ¢: Bata Medeling ¢. Data Testing Ans.a. Data Acquisition to calcul 12. Accuracy, Recall, Precision, F1 Score are the parameters q ; Q ati Uy a. Data Acquisition CO __ b. Data Evaluation late the efficiency under... ¢. Data Testing Oo Fe aaa Ans.b. Data Evaluation 13. Drawback/s of Rule-based approach is/are: i. The learning is static, ji, Any changes made to the original data will not be considered. (Once trained the model cannot improvise onthe basis of feedback, . All of the above statements are correct. Oo b, Statements | and i are correct © Statements ii and iii are correct. © _ 4. Statements i and iii are correct. Q Ans.a. All of the above statements are correct. 14. In... design is adaptive to change in data, which results in dynamicity of a model, tay ‘a, Learning-based Approach © _ b. Rule-based Approach 0 c. Data Acquisition oO d. Data Modelling 0 ‘Ans.b. Learning-based Approach ‘15! “~~ af modelled on human brain, itis essentially a machine learning algorithm, useful for solving prob when the dataset is large. ray a. Computer Vision © _ b. Data science 0 c. Natural Language Processing © 4. Neural Network 0 Ans.d, Neural Network 16. is nota Learning-based Approach where Al model gets trained on the data fed to it and then is able design a model which is adaptive to the change in data, (eo, a. Supervised Learning © __ b. Unsupervised Learning 0 ©. Reinforcement Learning © 4 Enforcement Leaming 0 ‘Ans.d. Enforcement Learning 17. Unsupervised Learning is divided into the following two categories, Identify the correct one. (00 a. Rule-based and Learning-based © _ ». Classification and Clustering 0 © Clustering and Dimensionality Reduction (C) — d, Classification and Regression 0 Ans.c. Clustering and Dimensionality Reduction 18. The 4 Ws Problem canvas helps in identi ig the key elements related to the problem. 4 Ws Problem canis a part of: poz a, Problem Scoping © _ b. Data Acquisition 0 © Modelling © 4. Evaluation 0 Ans.a. Problem Scoping 2. 182 | Touchpad Artificial Intelligence (Ver. 2.0)-xwe 106 gg Dat8 o™ e raining D2? resting Date fe airing D2? cc Bed 1 ees c ustering Seto be continuous. jon sb. classification syaation ist remodel 4, Problem Scoping «Data Exploration asd. Modeling fp cssfcation and Regression ae 2, Supervised, Learning «¢ Reinforcement, Learning jos. Supervised, Rule-based len pattems or trends identified out of it 1. Regression Cstering Anse. Clustering . Choose the correct option describing the feat Nervous System: block of 4 Ws Problem canvas helps in analysing the people geting ate" ‘Acquisition feeding previous data into the machine is called: _is one of the types of Supervised Learning Model, where data is clas he process of understanding the reliability of any AL model, bas ‘and comparing with actual answers, Therefore it must be followed by: a refers to the unsupervised learning algorithm ures of Neural Network. These are systems modelled on Hu ted directly C8 b, What d. Why oO oO b. Predicting Data O oO d. Evaluating Data i ding to labels and 0242 sified according se Oo Oo 1g test dataset into (2022 O° oO b. Classification d. Dimensionality reduction ed on outputs by feedin b. Data Acquisition oO O and approach followed is d. Modelling b. Unsupervised, Learning d. Supervised, Rule-based oO cording to the [2022] O O man Brain and 12022] which can cluster the unknown data a b. Classification O O 4, Dimensionality Reduction i itis essentially a machine learning algorithm. it tis useful when solving the problems for whi Statements i and ii are correct. , © Statements ii and ii are correct. 4. All of the above statements are correct. ii, They are able to extract feature without input from the prog} ich the data set is very large. Jammer. b. Statements i and iii are correct. ss 6 5 d. All of the above statements are correct. iAtProject Cycle | 183 “er LTE~ 26. Vijender has to maintain inventory on a daily basis, it usually takes 3-4 hours for a helper to take out raw materia, whi, in turns delays the production cycle and also delays the updation of stock. His manager has identified the problem ang looking for a possible solution. This is the task under: (2023, a. Problem Scoping © _ . Data Exploration oO . Data Evaluation O 4 Neural Network 0 Ans. a, Problem Scoping 27. The following are the key elements of (2023) i, Who are the stakeholders? ‘What is the problem? iii, Where does the problem arise? iv. Why do you believe that the problem is worth solving? a. We Problem Camas © |b. accuracy Precision Oa recar Ans. a. 4 Ws Problem Canvas oOo