A machine learning engineer is testing the speed at which his new computer graphics card can train a deep learning algorithm on a dataset. The engineer tested the speed of the graphics card on a dataset using the 10-fold cross-validation technique, which is testing 10 times the process. training-testing with the same dataset splitting size. From the 10 times of the training-testing process, the following training time data were obtained (in hours): 11,2 ; 10,1 ; 12,4 ; 11,0 ; 10,8 ; 12,2 ; 11,6 ; 12,4 ; 12,5 ; 10,6 a. Calculate the 99% two-sided confidence interval (99% two-sided confidence interval) for the graphics card's average training time. b. Calculate the upper 90% confidence interval (upper confidence interval of 90%) for the average training time of the graphics card. c. Calculate the 97.5% lower confidence interval (97.5% lower confidence interval) for the graphics card's average training time. d. Calculate the Margin of Error (MOE) of the graphics card's average training time with a 95% two-sided confidence interval.

A machine learning engineer is testing the speed at which his new computer graphics card can train a deep learning algorithm on a dataset. The engineer tested the speed of the graphics card on a dataset using the 10-fold cross-validation technique, which is testing 10 times the process. training-testing with the same dataset splitting size. From the 10 times of the training-testing process, the following training time data were obtained (in hours): 11,2 ; 10,1 ; 12,4 ; 11,0 ; 10,8 ; 12,2 ; 11,6 ; 12,4 ; 12,5 ; 10,6 a. Calculate the 99% two-sided confidence interval (99% two-sided confidence interval) for the graphics card's average training time. b. Calculate the upper 90% confidence interval (upper confidence interval of 90%) for the average training time of the graphics card. c. Calculate the 97.5% lower confidence interval (97.5% lower confidence interval) for the graphics card's average training time. d. Calculate the Margin of Error (MOE) of the graphics card's average training time with a 95% two-sided confidence interval.

A First Course in Probability (10th Edition)

10th Edition

ISBN:9780134753119

Author:Sheldon Ross

Publisher:Sheldon Ross

Chapter1: Combinatorial Analysis

Section: Chapter Questions

Problem 1.1P: a. How many different 7-place license plates are possible if the first 2 places are for letters and...

See similar textbooks

Similar questions

Take a look at the following scatter plot of the so-called XOR data-set: It is a classification data-set with the goal of separating the red and the black observations. Assume, that thenumber of red and black observations is approximately equal. Which of the following statements is correct?a) A Decision Tree can reach a prediction error of (nearly) zero on this data-set.b) When performing a variable selection using the step-wise forward selection algorithm, neither of the variablesx1, x2 will be added to the model.c) A Linear Discriminant Analysis (LDA) can reach a prediction error of (nearly) zero on this data-set.d) Every model using only one of the two variables x1, x2 will have a missclassification error of approximately 50%.
which option is correct The data mining term of "score" is known as a(n) _______________ in statistical terminology. Multiple Choice forecast record algorithm feature
A study was performed concerning medical emergencies on commercial airline flights. A database was constructed based on calls to a medical communications center from 5 domestic and international airlines representing approximately 15% of the global passenger flight volume from January 2005 to December 2007. There were 11,000 in flight medical emergencies (IFM) among 8,000,000 flights during the study period. Assume that there is at most 1 IFM per flight. Suppose a flight attendant works on 3 flights per day for each of 300 days per year. Also, assume that the flight attendant’s total duration of employment is 20 years. What is the approximate probability that he/she encounter at least 5 IFM’s over a 20 year period? (b) Suppose we observe 80 alcoholics with cirrhosis of the liver, of whom 25 have hepatomas, that is, liver cell carcinoma. Suppose we know, based on a large sample, that t`he risk of hepatoma among alcoholics without cirrhosis of the liver is 25%. What is the approximate…
People are classified as hypertensive if their systolic blood pressure (SBP) is higher than a specified level for their age group, according to the algorithm in the table below. Assume SBP is normally distributed with mean, and standard given in the table for age groups 1 – 14 and 15 – 44, respectively. Define a family as a group of two people in age group 1 – 14 and two people in age group 15 – 44. A family is classified as hypertensive if at least one adult and at least one child are hypertensive. i. What proportion of 1 – 14-year-olds are hypertensive? ii. What proportion of 15 – 44-year-olds are hypertensive?
A plant physiologist studying a small beach-dwelling plant called the Great Lakes sea rocket, Cakile edentula, wondered if the plants grew faster in competition with non-kin plants than when in competition with seedlings that are close relatives. She set up a direct study of kin recognition by growing sets of four seeds in one container. When the seedlings reached a phase of vigorous root growth, about 8 weeks after planting, she carefully removed the soil and weighed the root masses. Plants grouped with siblings had the following root weight statistics: n = 24 X = 6.25 g s = 0.47 g Plants grouped with unrelated seedlings had the following root weight statistics: n = 20 X = 7.22 g s = 0.55 g Are the plants grown in competition with unrelated individuals allocating sig- nificantly more resources to root growth than those growing among relatives?
People are classified as hypertensive if their systolic bloodpressure (SBP) is higher than a specified level for their agegroup, according to the algorithm in Table 5.1.Assume SBP is normally distributed with mean andstandard deviation given in Table 5.1 for age groups 1−14and 15−44, respectively. Define a family as a group of twopeople in age group 1−14 and two people in age group15−44. A family is classified as hypertensive if at least oneadult and at least one child are hypertensive. 5.17) What proportion of 1- to 14-year-olds are hypertensive? 5.18) What proportion of 15- to 44-year-olds are hyper-tensive?
What is the hand computation step by step with the guidlines of the software? Your professor is interested in determining if mode of presentation affects how prose material is remembered. She used one prose passage that was presented visually and auditorily. From 200 undergraduate students in the university, only 10agreed to participate. On the first day of the experiment, the 10participants receives visual presentation of the prose passage while on the second day, same participants hears the passages through an auditory presentation. At the end of each presentations, participants were asked to say as much of the material as they can remember within 2 minutes. The words remembered were obtained. Use Student’s tTest for Correlated Groups, alpha at .05 2 tail Visual - 4 2 5 8 2 3 3 2 5 6 Auditory- 4 4 5 9 8 4 4 5 8 6
A systems analyst tests a new algorithm designed to work faster than the currently-used algorithm. Each algorithm is applied to a group of 38 sample problems. The new algorithm completes the sample problems with a mean time of 22.07 hours. The current algorithm completes the sample problems with a mean time of 22.33 hours. Assume the population standard deviation for the new algorithm is 4.674 hours, while the current algorithm has a population standard deviation of 5.185 hours. Conduct a hypothesis test at the 0.05 level of significance of the claim that the new algorithm has a lower mean completion time than the current algorithm. Let ?1be the true mean completion time for the new algorithm and ?2 be the true mean completion time for the current algorithm. Pay attention to spaces between words. H0: Ha: z-Test Statistic (round to two decimal places) = p-value (round to four decimal places) = Conclusion (write "R" for reject H0, and "F" for fail to reject H0):
In many colleges, educators are changing their approach to instruction from a “teacher/lecture-centeredmodel” to a “student-centered model” where students learn in a laboratory environment in which lectureis deemphasized and students can proceed at a pace suitable to their learning needs. In once schoolwhere this model was being introduced, of the 743 students who enrolled in the traditional lecture model, 364 passed; of the 567 in the student-centered model, 335 passed. Use a 0.05 level ofsignificance to test the claim that student-centered model results in a higher pass rate than the traditionalmodel?
Consider the following research hypothesis and the p-value obtained via a statistical test. Would this testing have involved one-sample or two-sample hypothesis testing? Does the scenario involved paired or independent samples?Assuming the appropriate testing was used, what would be an appropriate conclusion to draw given the reported results and p-value?Explain the reasoning for your answers.The hypothesis is that students who are familiar with the Theory of Algorithms learn the programming language C++ faster than students who are not familiar with this theory. We have gathered data from 50 students who are familiar with the Theory of Algorithms (Group 1) and 40 students who are not familiar with the Theory of Algorithms (Group 2). Experiments showed students from Group 1 took a mean of 36.5 hours to complete the training course of C++, while students Group 2 the mean was 39.1 hours. The p-value was 0.04.
6. A researcher develop one new prediction algorithm. He want to find out whether hisalgorithm predict a situation faster than the current method. He test his algorithm to makea prediction base on 4 sets of data. He recorded the computation time in microsecond andcompare it with current method and standard method. Table 5 give the computation timefor all method tested.TABLE 5Proposed Method Current Method Standard Method10 11 1313 16 177 9 915 16 19At 2.5% significance level, will you conclude that the computation time taken to predict is thedifferent for each of the three algorithms.
Consider the following research hypothesis and the p-value obtainedvia a statistical test. Would this testing have involved one-sample or two-sample hypothesis testing? Does the scenario involved paired or independent samples?Assuming the appropriate testing was used, what would be an appropriate conclusion to draw given the reported results and p-value? Explain the reasoning for your answers. The hypothesis is that students who are familiar with the Theory of Algorithms learn the programming language C++ faster than students who are not familiar with this theory. We have gathered data from 30 students who are familiar with the Theory of Algorithms (Group 1) and 30 students who are not familiar with the Theory of Algorithms (Group 2). Experiments showed students from Group 1 took a mean of 32.5 hours to complete the training course of C++, while students Group 2 the mean was 42.1 hours. The p-value was 0.14