cs4001_2024T2_Q1_NA.pdf

Assume you are using mini-batch gradient descent with a total dataset size of 1,000 and a batch size of 20. If you process 10,000 mini-batches, how many epochs have been completed?

If the batch size in mini-batch gradient descent is increased from 32 to 128 while keeping all other parameters constant, what is the likely impact on the variance of the gradient estimates per update?

What do contour lines on a contour plot represent?

**Instructions:** The exam is pen & paper based and should be answered in the sheets provided to you. **Part A (Multiple Choice Questions):** Each question has four choices, out of which only one is the correct answer. (8×2=16 marks) 1. In a survey about favorite ice cream flavors, the column indicating the flavor chosen by each respondent would be considered what type of data? A. Categorical data B. Ordinal data C. Interval data D. Ratio data 2. What type of data is represented by the visualization shown in the figure given below? [[IMAGE:0e05a43849c6870a_3_0]] A. Temporal B. Hierarchical C. Network-based D. Geospatial 3. Which of the following scenarios best exemplifies ordinal data? A. Recording the temperatures of different cities in Celsius. B. Ranking movies based on their box office earnings. C. Measuring the heights of students in a classroom. D. Counting the number of pages in a book. 4. What does the diagram in the visualization shown below analytical represents? [[IMAGE:0e05a43849c6870a_4_1]] A. Correlation B. Distribution C. Flow D. Ranking 5. What is the primary purpose of retaining key landmarks on transport network maps? A. They give a unique character to the map B. To provide historical context C. To aid in orienting passengers D. They help to recognize the city 6. Based on the visualization provided, what was the primary inference drawn by Dr. Snow regarding the transmission of Cholera within the city? [[IMAGE:0e05a43849c6870a_4_2]] A. The fatalities from Cholera are reaching a plateau. B. The time series data is not well-suited for the intended analysis C. There was a notable surge in fatalities in the initial week of September 1854. D. The combined fatalities during August and September are being considered. 7. The following map shows the migration of people from various cities to Delhi. It is an example of _________. [[IMAGE:0e05a43849c6870a_5_3]] A. Choropleth B. Cartogram C. Isopleth D. Flow maps 8. Which of the following best describes the given picture scenario? [[IMAGE:0e05a43849c6870a_5_4]] A. Visual confirmation B. Visual discovery C. Idea generation D. Idea illustration

**Part B – Multiple Select Question:** For the following questions, out of which one or more than one choice(s) is the correct answer. (6×3=18 marks) 1. Which of the following scenarios best illustrates derived data? A. Recording the average rainfall in a region over the past decade B. Collecting the number of cars passing through a toll booth each day C. Measuring the length of a river using GPS coordinates D. Combining population data with geographic data to create population density data E. Estimating the market value of a company based on its financial reports 2. In a study analyzing the effectiveness of different heating systems in homes, researchers collected temperature data from various rooms in houses equipped with different heating systems. Which of the following best describes the nature of the temperature data collected in the study? A. The temperature data is best characterized as categorical data because it represents different heating systems. B. The temperature data is categorized as ordinal data because it can be ordered based on the effectiveness of the heating systems. C. The temperature data is represented as interval data because the differences between temperature measurements are meaningful. D. The temperature data is categorized as ratio data because it possesses a true zero point indicating the absence of temperature. 3. Which of the following statements accurately describes the importance of data semantics? A. Data semantics primarily concerns the aesthetics of data visualizations. B. Semantically rich data simplifies the process of data cleaning. C. Consistent data semantics ensures uniformity in visual representations. D. Data semantics do not impact the audience's engagement with visualizations. E. Data semantics have no impact on uncovering hidden patterns within datasets. F. Semantically rich data facilitates clearer communication of insights. 4. Select the accurate statements regarding specific visualization types: A. Pie charts are suitable for displaying trends over time. B. Bubble charts are effective for illustrating the hierarchical structure of data. C. Treemaps are suitable for illustrating the hierarchical structure of categories. D. Heatmaps are primarily utilized to visualize changes in data over time. E. Scatter plots are ideal for showing correlations between two variables. 5. Which of the following statements regarding geospatial visualizations is/are correct? A. Isopleths are adept at illustrating patterns in continuous data, such as temperature gradients. B. Isopleths are primarily designed for showcasing discrete and categorical data. C. Choropleth maps effectively convey variations in data across geographic regions using color gradients. D. Isopleths and Choropleths are interchangeable terms describing the same mapping technique. 6. Which statements accurately describe the characteristics of the provided visualizations? A. Funnel charts can be used to represent the correlation between two variables. B. Sankey diagrams depict the flow of information or resources between categories. C. Ridgelines are used to visualize the distribution of data in various categories. D. Choropleths display data using different shades or colors within predefined geographic areas.

**Part C – Short Answer Questions:** Write 100-150 words answers to each question. Answer using pen & paper using the paper provided to you. (2x8=16 marks) 1. Given below are 2 charts. The first chart is about Media rights of some of the biggest domestic franchise sports leagues in the world and IPL’s place in it. The second chart shows the change in voters and electors in % terms between the 2019 and 2024 parliamentary elections in India. Identify the key insight that each of the charts is attempting to highlight and critically analyze how much they have succeeded in communicating it. $40 min Broadcast rights amount per match 35 30 25 20 a) 10 NFL 272 matches @ ina season IPL e 79 matches Premier League 380 matches e e @ LaLiga | 380 matches Bundesliga e @ National Basketball Association | |,230 matches Major League Baseball | 2.430 matches Sibin eI 3 4 <) 6 @ 8 9 10 Annual broadcasting rights [[IMAGE:0e05a43849c6870a_9_6]] 2. Critically analyze the visualization comparing dairy milk and plant-based "milks", and suggest at least two redesigns with improvements. [[IMAGE:0e05a43849c6870a_10_7]]