(1) Be able to practice interval estimation for population mean, population variance, and population proportion.
(2) Be able to practice testing for population mean and variance.
(3) Be able to practice regression analysis.
(4) You can create Python programs related to artificial intelligence using Google Collaboratory.
Outline:
AI・MOTⅡ will include lectures and practical training on the application of AI・MOTⅠ. Let's review why robotics, data science, and artificial intelligence technologies are needed to extend MOT. After that, you will learn the flow of practical programs and types of machine learning through exercises about machine learning related to regression, classification, and clustering using Python programs. At the same time, we will review the basic statistics and learn about the fundamental principles of black box algorithms. The low-code and no-code era has already arrived, and you will learn about the connections between statistics, data science, and artificial intelligence necessary for MOT in the low-code and no-code era. Through the study of this subject, the goal is to acquire basic redux regarding AI and MOT, which will lead to the following topics principal component analysis, dimension reduction, neural networks, deep learning, and deep learning using generative adversarial networks.
Style:
〇Lectures and exercises will be held. There are many assignments, so please do not miss anything. The evaluation will be based on 50% of midterm exams in the first half and 50% on multiple reports throughout the course.
〇The report has a large amount of home assignments. Therefore, there is a lot of individual work, and individual qualifications are evaluated based on the quality of the report.
〇 Preparatory study in advance: Review the previous lecture and prepare for the lesson, then learn what you want for the class.
〇 (Out-of-class study/in advance) Prepare for the lesson content.
〇(Out-of-class study/after-class study) Solve problems related to the class content.
Notice:
〇Classes and program exercises will be held in the classroom. Learn both theory and practice. In this subject, credits will be recognized if you score 60 points or higher.
〇 Meeting deadlines for report assignments is highly evaluated. You will be deducted 3 points for every day you are late, so please make sure to submit your application on time.
〇If the evaluation is less than 60 points, you can take a supplementary test upon request. Those who are approved to have earned credits as a result of the confirmation examination will receive a score of 60 points.
〇We will distribute prints and share digital prints as much as possible.
〇 For classes, you will need to bring a BYOD-purchased PC and your own Google account.
|
|
|
Theme |
Goals |
| 2nd Semester |
| 3rd Quarter |
| 1st |
〇The era and MOT when Japan specialized in mass production.
〇What are the good product rate and defective product rate?
〇What is yield rate?
〇Modern production systems cannot be imagined without MOT.
〇Production factories where the decline in the working population has progressed ahead of others.
〇What is working in factories instead of humans?
〇Introduction of Google Collaboratory. |
〇Learn why MOT is necessary and why instrumentation technology and artificial intelligence are needed as an extension of MOT.
〇Learn that there are things you can do and things you cannot do in production activities.
〇 Understand design quality and manufacturing quality.
〇Understand the good product rate and defective product rate.
〇I can understand yield.
〇I understand that improving product quality will reduce costs and increase profits.
〇 I can understand who conducts all product inspections.
〇Understand that product quality control is based on statistics.
|
| 2nd |
〇What is the binomial theorem?
〇What is moment generating function?
〇What is Poisson distribution?
〇What is normal distribution? |
〇Understand the binomial theorem.
〇Be able to understand moment generating functions.
〇Be able to understand Poisson distribution.
〇Understand normal distribution.
|
| 3rd |
〇What are descriptive statistics and inferential statistics?
〇Statistics review, mean, variance, standard deviation
〇What is the sample mean?
〇What is unbiased variance as sample variance?
〇What is the standard normal portion? |
〇You can understand that the costs are completely different between descriptive statistics based on 100% checking and inferential statistics based on sampling.
〇As a refresher on statistics, you will be able to understand the mean, variance, and standard deviation.
〇Be able to understand sample mean.
〇Be able to understand unbiased variance.
〇Be able to understand what a standard normal fraction is.
|
| 4th |
〇What are point estimation and interval estimation?
〇What is interval estimation and confidence interval?
〇How to find the confidence interval.
〇What are large and small samples?
〇What are the population mean, population variance, and population ratio?
〇What is the null hypothesis?
〇What is the test statistic t? |
Understand what point estimation and interval estimation are.
〇I understand that sampling costs money.
〇Understand why interval estimation is necessary in modern mass production systems.
〇Be able to understand what interval estimation and confidence intervals are.
〇 Confidence intervals can be determined.
〇Be able to explain what a large sample and a small sample are.
〇Be able to explain what the population mean, population variance, and population ratio are.
〇I understand what the null hypothesis is.
〇Be able to understand the test statistic t.
You can test the test statistic t from the number table.
|
| 5th |
〇What is a difference test?
〇What are observed frequency and expected frequency?
〇How to express the variation in the difference between observed frequency and expected frequency
〇Introduction of an example where the difference (displacement) is expressed as a square.
〇What is the chi-square test?
〇What is degree of freedom?
〇 Chi-square distribution that changes significantly depending on degrees of freedom |
〇Be able to understand the difference test.
〇Be able to understand observed frequency and expected frequency.
〇Be able to understand how to express the variation in the difference between observed frequency and expected frequency.
〇Differences (displacements) are expressed as squares, and you can understand that there are many other differences that are expressed as squares.
〇Be able to understand the chi-square test.
〇Be able to understand what degrees of freedom are.
〇Be able to understand the characteristics of the chi-square distribution, which varies greatly depending on the degrees of freedom.
|
| 6th |
〇How can we determine whether there is a difference (displacement) between the averages of two samples?
〇What is the t-test?
〇 Comparison of t distribution with 30 or more degrees of freedom and normal distribution
〇 Regarding the notation of the test statistic t for the difference when the population variance is known
〇 Regarding the notation of the test statistic t for the difference when the population variance is unknown |
〇Be able to understand whether there is a difference between the average values of two samples or not.
〇If the number of samples for each of Sample A and Sample B is small, taken from populations A and B that follow normal distributions, you will be able to understand what is the distribution of the difference in the mean values of those small samples.
〇Be able to understand what a t-distribution table is.
|
| 7th |
〇 How to determine whether there is a difference between the averages of three or more samples?
〇What is variance analysis?
〇What is F value? |
〇Be able to explain what analysis of variance is.
〇Explain how to determine whether there is a gap between three or more samples.
〇Be able to explain what an F distribution table is.
|
| 8th |
〇Midterm exam (50% of evaluation)
|
〇Achievement test was conducted to confirm what was learned by the midterm of the first semester.
|
| 4th Quarter |
| 9th |
〇Intermediate exam explanation
〇Theoretical method for obtaining Poisson distribution and normal distribution from the binomial theorem. Part 1 |
〇 Intermediate exam explanation
〇 Poisson distribution and normal distribution can be calculated from the binomial theorem while copying and memorizing the materials prepared by the instructor by hand. Understand the theoretical background.
|
| 10th |
〇Theoretical method for obtaining Poisson distribution and normal distribution from the binomial theorem. Part 2
〇Why hand-written programs in the low-code and no-code era?
〇What is the difference between a program consumer and a developer/pioneer/problem solver?
〇Exercise using Python Part 1 Chapter 1 What is machine learning?
〇Report assignment ① |
〇 Poisson distribution and normal distribution can be calculated from the binomial theorem while copying and memorizing the materials prepared by the instructor by hand. Understand the theoretical background.
〇Be able to explain low code and no code
〇Be able to explain that job opportunities for graduates of the Department of Mechanical Systems Engineering require problem-solving ability.
〇Understand modern statistical methods according to the textbook. Part 1 Chapter 1
|
| 11th |
〇How to find a regression line using the least squares method. Part 1
〇Exercise using Python Part 2 Chapter 1 Difference between data analysis and machine learning |
〇Understand the theory of regression analysis while copying and memorizing the materials prepared by the instructor by hand.
〇Understand modern statistical methods according to the textbook. Part 2 Chapter 1
|
| 12th |
〇How to find a regression line using the least squares method. Part 2
〇Exercises using Python Part 3 Chapter 2 How to use the standard library Scikit-Learn
〇Report assignment ② |
〇Understand the theory of regression analysis while copying and memorizing the materials prepared by the instructor by hand.
〇Understand modern statistical methods according to the textbook. Part 3 Chapter 2 (Report assignment)
|
| 13th |
〇Theoretical explanation of chi-square distribution
〇Exercises using Python Part 4 Chapter 2 How to use the standard library Scikit-Learn
〇Report assignment ③ |
〇Listening and understanding the theoretical explanation of the chi-square distribution while copying and memorizing the materials prepared by the instructor by hand.
〇Exercise using Python Part 4 Chapter 2
|
| 14th |
〇Theoretical explanation of t distribution
〇Exercises using Python Part 5 Chapter 3 Learn the steps of machine learning
〇Report assignment ④ |
〇Listening and understanding the theoretical explanation of the t-squared distribution while copying and memorizing the materials prepared by the instructor by hand.
〇Exercise using Python Part 5 Chapter 3
|
| 15th |
〇Theoretical explanation of F-th power distribution
〇Exercises using Python Part 6 Chapter 3 Learn the steps of machine learning
〇Report assignment ⑤ |
〇Listening and understanding the theoretical explanation of the F-squared distribution while copying and memorizing the materials prepared by the instructor by hand.
〇Exercise using Python Part 6 Chapter 3
|
| 16th |
〇Confirmation of evaluation and number of absences
〇Self-evaluation and class evaluation using questionnaires |
〇Confirmation of evaluation and number of absences
〇Self-evaluation and class evaluation using questionnaires
|