We may earn an affiliate commission when you visit our partners.
Brent Summers
본 강의에서는 머신 러닝의 공정성과 편향에 대한 근본적인 문제를 배웁니다. 대학교 입학부터 대출 허가까지, 예측 모델을 이용해 만드는 중요한 결정이 늘어나면서, 모델이 불공정한 예측을 만들지 않게 하는 것이 굉장히 중요해졌습니다. 인간에서 비롯된 편향부터 데이터 세트 인지까지, 윤리적인 모델 구축의 여러 방면을 알아보겠습니다.
Register for this course and see more details by visiting:
OpenCourser.com/course/n0jqxl/ingong
Three deals to help you save
We found three deals and offers that may be relevant to this course.
Save money when you learn.
All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.
Valid until December 12
Annual Subscription Savings
Unlock programs from Google, Microsoft, and IBM and join 77% of learners who reported positive career outcomes.
Only $239!
Valid for a limited time only
Future-proof your career
Access O'Reilly books, live events, courses, and more. Save with an annual subscription.
Take
15%
off
What's inside
Syllabus
머신 러닝의 공정성과 보호
강의에 오신 여러분, 환영합니다! 1주 차에는 머신 러닝의 맥락에서 공정성이 무엇을 의미하는지, 여러 시나리오에서의 참 패리티가 무엇을 의미하는지 이야기합니다.
공정한 모델 구축: 이론과 연습
이번 주에는 불공정에 맞서볼 겁니다. 공정성 문제를 이해했으니, 공정성을 위반하지 않는 모델을 구축하는 방법을 알아봅시다.
Read more
Syllabus
머신 러닝의 공정성과 보호
강의에 오신 여러분, 환영합니다! 1주 차에는 머신 러닝의 맥락에서 공정성이 무엇을 의미하는지, 여러 시나리오에서의 참 패리티가 무엇을 의미하는지 이야기합니다.
공정한 모델 구축: 이론과 연습
이번 주에는 불공정에 맞서볼 겁니다. 공정성 문제를 이해했으니, 공정성을 위반하지 않는 모델을 구축하는 방법을 알아봅시다.
Read more
인적 요소: 데이터 편향 최소화하기
이번 주에는 데이터 수집 및 속성 선택 과정에서 일어나는 편향 중 인간에서 비롯된 편향을 알아보겠습니다. 목표는 모델을 구축하기 전에 편향을 제거하는 겁니다.
Good to know
Good to know
Know what's good ,
what to watch for , and
possible dealbreakers
Explores fairness and bias in machine learning, which is currently in high demand across industries
Taught by highly experienced instructor Brent Summers, who is well-respected for developing fairness evaluation tools in venture capital and business
Develops foundational understanding of fairness and bias, which are critical skills for data scientists, machine learning engineers, and decision-makers
Save this course
Save 인공 지능 데이터 공정성 및 편향 to your list so you can find it easily later:
Save
Save
Activities
Be better prepared
before
your course. Deepen your understanding
during
and
after
it. Supplement your coursework and achieve mastery of the topics covered
in 인공 지능 데이터 공정성 및 편향 with these
activities:
Review data collection methods
Show steps
Refresh your existing data collection skills by reviewing different methods and ensuring you are able to identify what is appropriate for your own research.
Browse courses on
Data Collection
Show steps
Brush up on statistical concepts
Show steps
Recall foundational statistical concepts that will be used throughout this course.
Browse courses on
Statistics
Show steps
-
Revise key statistical distributions, such as normal, binomial, and Poisson distributions.
-
Review linear regression and logistic regression concepts.
Solve practice problems on model evaluation metrics
Show steps
Sharpen your understanding of model evaluation metrics through dedicated practice.
Show steps
-
Find online platforms or textbooks that provide practice problems on metrics like accuracy, precision, and recall.
-
Regularly solve these problems to enhance your proficiency in evaluating model performance.
Five other activities
Expand to see all activities and additional details
Show all eight activities
Complete tutorials on bias and fairness in machine learning
Show steps
Explore in-depth tutorials to grasp the nuances of bias and fairness in machine learning.
Browse courses on
Machine Learning Bias
Show steps
-
Find tutorials that cover bias mitigation techniques, such as reweighting and adversarial training.
-
Work through examples and practice implementing these techniques in your own code.
Participate in study groups to discuss course concepts
Show steps
Engage with peers to clarify concepts, share insights, and reinforce your understanding.
Show steps
-
Form or join a study group with classmates who share similar learning goals.
-
Meet regularly to discuss lecture material, assignments, and any challenges you encounter.
-
Collaborate on assignments and projects to benefit from diverse perspectives.
Connect with experts in the field of machine learning fairness
Show steps
Seek guidance and mentorship from professionals who can provide valuable insights and support.
Show steps
-
Attend industry events, conferences, or webinars to meet professionals in the field.
-
Reach out to researchers or practitioners via email or LinkedIn to express your interest in their work.
-
Present your own research or projects at conferences or meetups to gain recognition and connect with potential mentors.
Contribute to open-source projects related to machine learning fairness
Show steps
Gain hands-on experience by contributing to real-world projects that promote fairness in machine learning.
Browse courses on
Machine Learning Fairness
Show steps
-
Identify open-source projects that align with your interests and skillset.
-
Start by contributing in small ways, such as fixing bugs or writing documentation.
-
Gradually take on more challenging tasks and responsibilities within the project.
Develop a data visualization tool to explore bias and fairness in datasets
Show steps
Create a tool that enables you to visually analyze and identify potential biases or fairness issues in datasets.
Browse courses on
Data Visualization
Show steps
-
Research and explore existing data visualization techniques for bias detection.
-
Design and develop a prototype of your data visualization tool.
-
Test and refine your tool using real-world datasets and evaluate its effectiveness in identifying biases.
Review data collection methods
Show steps
Refresh your existing data collection skills by reviewing different methods and ensuring you are able to identify what is appropriate for your own research.
Browse courses on
Data Collection
Show steps
Show steps
Show steps
Brush up on statistical concepts
Show steps
Recall foundational statistical concepts that will be used throughout this course.
Browse courses on
Statistics
Show steps
Show steps
Show steps
- Revise key statistical distributions, such as normal, binomial, and Poisson distributions.
- Review linear regression and logistic regression concepts.
Solve practice problems on model evaluation metrics
Show steps
Sharpen your understanding of model evaluation metrics through dedicated practice.
Show steps
Show steps
Show steps
- Find online platforms or textbooks that provide practice problems on metrics like accuracy, precision, and recall.
- Regularly solve these problems to enhance your proficiency in evaluating model performance.
Five other activities
Expand to see all activities and additional details
Show all eight activities
Complete tutorials on bias and fairness in machine learning
Show steps
Explore in-depth tutorials to grasp the nuances of bias and fairness in machine learning.
Browse courses on
Machine Learning Bias
Show steps
Show steps
Show steps
- Find tutorials that cover bias mitigation techniques, such as reweighting and adversarial training.
- Work through examples and practice implementing these techniques in your own code.
Participate in study groups to discuss course concepts
Show steps
Engage with peers to clarify concepts, share insights, and reinforce your understanding.
Show steps
Show steps
Show steps
- Form or join a study group with classmates who share similar learning goals.
- Meet regularly to discuss lecture material, assignments, and any challenges you encounter.
- Collaborate on assignments and projects to benefit from diverse perspectives.
Connect with experts in the field of machine learning fairness
Show steps
Seek guidance and mentorship from professionals who can provide valuable insights and support.
Show steps
Show steps
Show steps
- Attend industry events, conferences, or webinars to meet professionals in the field.
- Reach out to researchers or practitioners via email or LinkedIn to express your interest in their work.
- Present your own research or projects at conferences or meetups to gain recognition and connect with potential mentors.
Contribute to open-source projects related to machine learning fairness
Show steps
Gain hands-on experience by contributing to real-world projects that promote fairness in machine learning.
Browse courses on
Machine Learning Fairness
Show steps
Show steps
Show steps
- Identify open-source projects that align with your interests and skillset.
- Start by contributing in small ways, such as fixing bugs or writing documentation.
- Gradually take on more challenging tasks and responsibilities within the project.
Develop a data visualization tool to explore bias and fairness in datasets
Show steps
Create a tool that enables you to visually analyze and identify potential biases or fairness issues in datasets.
Browse courses on
Data Visualization
Show steps
Show steps
Show steps
- Research and explore existing data visualization techniques for bias detection.
- Design and develop a prototype of your data visualization tool.
- Test and refine your tool using real-world datasets and evaluate its effectiveness in identifying biases.
Career center
Learners who complete 인공 지능 데이터 공정성 및 편향 will develop knowledge and skills
that may be useful to these careers:
Statistician
Statistician
Statisticians apply statistical methods to collect, analyze, interpret, and present data for a variety of purposes. This course may be useful for a Statistician because it provides methods for analyzing and mitigating data bias.
Director of Data
Director of Data
The Director of Data is responsible for the overall strategy and management of the organization's data. This course may be useful for a Director of Data who wants to steer the organization towards using data in a responsible and unbiased way.
Risk Analyst
Risk Analyst
Risk Analysts identify, assess, and mitigate potential risks for businesses. This course may be useful for a Risk Analyst by providing tactics to minimize the potential for biased outcomes.
Data Architect
Data Architect
Data Architects design and build data architectures for organizations. This course may be useful for a Data Architect who wants to make sure that the organization's data infrastructure minimizes bias.
Software Engineer
Software Engineer
Software Engineers design, develop, and maintain software systems. This course may be useful for those who want to use their software engineering skills to mitigate bias in machine learning algorithms.
Product Manager
Product Manager
Product Managers are responsible for the development and launch of new products and features. This course may be useful for a Product Manager so they can ensure that machine learning-based products are not biased.
Actuary
Actuary
Actuaries apply mathematical and statistical methods to assess risk for insurance companies and other financial institutions. This course may be useful for an Actuary because it provides insights into the ethical implications of data science.
Data Protection Officer
Data Protection Officer
Data Protection Officers are responsible for ensuring that an organization complies with data protection laws and regulations. This course may be useful for a Data Protection Officer who needs to understand the ethical implications of data use.
Data Governance Analyst
Data Governance Analyst
Data Governance Analysts develop and implement policies and procedures to ensure the proper use of data within an organization. This course may be useful for a Data Governance Analyst who wants to encourage equitable and ethical data practices throughout the organization.
Business Analyst
Business Analyst
Business Analysts provide insights to businesses by analyzing processes, systems, policies, and data. This course may be useful for a Business Analyst so they can advocate for the ethical use of data science and AI within the organization.
Quantitative Analyst
Quantitative Analyst
Quantitative Analysts create mathematical models to assess risk, predict trends, and optimize decision-making for investment and trading strategies. This course may be useful to a Quantitative Analyst because it covers ways to minimize bias in modeling.
Data Analyst
Data Analyst
Data Analysts collect, clean, and analyze data in order to extract insights and inform decision-making. This course may be useful for a Data Analyst because it discusses ways to recognize and eliminate data bias.
Technical Writer
Technical Writer
Technical Writers create user guides and other documentation for technical products. This course may be useful for a Technical Writer who needs to explain complex machine learning concepts to a non-technical audience in a way that is clear and unbiased.
Machine Learning Engineer
Machine Learning Engineer
Machine Learning Engineers develop, implement, and maintain machine learning, deep learning, and statistical models for the organization's use. This course can help the Machine Learning Engineer ensure that the models they implement are fair and unbiased.
Data Scientist
Data Scientist
A Data Scientist employs substantial amounts of data to create machine learning models and/or predictive analytics that can predict or optimize a given outcome. This course may be useful to a Data Scientist because it offers strategies for removing bias from data and building equitable models.
For more career information including salaries, visit:
OpenCourser.com/course/n0jqxl/ingong
Reading list
We've selected 11 books
that we think will supplement your
learning. Use these to
develop background knowledge, enrich your coursework, and gain a
deeper understanding of the topics covered in
인공 지능 데이터 공정성 및 편향.
Examines the ethical implications of algorithms and provides a theoretical framework for designing fair and ethical algorithms.
이 책은 기계 학습 모델에서 공정성을 보장하는 데 중점을 두고 있으며, 편향을 측정하고 완화하는 다양한 기술을 다룹니다.
Examines the use of AI in surveillance, policing, and criminal justice systems, highlighting the potential for bias and discrimination against marginalized communities.
이 책은 기계 학습의 기본 사항에 대한 실용적인 안내서로서, 편향 완화를 포함한 주요 주제를 다룹니다.
Critically examines the use of mathematical models and algorithms in decision-making processes, exposing the potential for bias and discrimination.
이 책은 기계 학습 라이브러리를 사용하는 실습 가이드로서, 편향 완화 및 모델 평가를 포함한 주제를 다룹니다.
이 책은 기계 학습을 위한 R 프로그래밍 언어 가이드로서, 편향 완화 및 모델 평가를 포함한 주제를 다룹니다.
이 책은 통계 학습의 초보자를 위한 포괄적인 안내서로서, 편향 완화에 대한 장을 포함한 주요 주제를 다룹니다.
이 책은 통계 학습의 기본 개념과 기법을 다루며, 편향 추정과 모델 선택을 포함한 주제를 다룹니다.
이 책은 파이썬 프로그래밍 언어를 배우기 위한 초보자 가이드로서, 데이터 분석 및 자동화를 위한 기본 기술을 제공합니다.
Provides a comprehensive introduction to Python for data analysis, covering the basics of data structures, algorithms, and statistical modeling.
For more information about how these books relate to this course, visit:
OpenCourser.com/course/n0jqxl/ingong
Share
Similar courses
Similar courses are unavailable at this time. Please try again later.
Level
Introductory
Via
Coursera
Institution
LearnQuest
Instructor
Brent Summers
Language
한국어
Transcripts
English
Español
Français
Português
日本語
Pусский
Good to know
Explores fairness and bias in machine learning, which is currently in high demand across industries
Taught by highly experienced instructor Brent Summers, who is well-respected for developing fairness evaluation tools in venture capital and business
Develops foundational understanding of fairness and bias, which are critical skills for data scientists, machine learning engineers, and decision-makers
Our mission
OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.
Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.
Find this site helpful? Tell a friend about us.
Affiliate disclosure
We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.
Your purchases help us maintain our catalog and keep our servers humming without ads.
Thank you for supporting OpenCourser.
© 2016 - 2024 OpenCourser