한국어
로그인

AI 및 머신러닝 소개 | AI & Python 코딩 수업 1급

수업
Play
David Sofield
평균 평점:
4.9
수강 후기 수:
(735)
인기 수업
인공 지능과 기계 학습에 대한 소개로서 학습자에게 이러한 흥미로운 분야를 소개합니다. 학생들은 실제 기계 학습 도구, Python 코드 및 실제 데이터를 사용하여 4개의 기계 학습 프로젝트를 완료합니다.
보고계신 지문은 자동 번역 되었습니다

수업 소개

영어레벨 - B2+
미국 7 - 10 학년
레벨 Beginner
10 lessons//10 Weeks
 Week 1
Lesson 1
Introduction to AI and Machine Learning
Students will explore the concepts of intelligence and AI, discovering how AI is integrated into our daily lives. They'll learn the distinction between AI, Machine Learning, and Data Science, and get hands-on experience with Google Colab, a powerful tool for coding and analysis.
 Week 2
Lesson 2
Fundamentals of Machine Learning and Python
This session introduces different types of Machine Learning and dives into essential Python libraries like NumPy and Pandas. Students will begin their first ML project, predicting favorite music, which will give them a practical understanding of ML applications.
 Week 3
Lesson 3
Machine Learning Concepts and Data Visualization
Students will complete their first ML project and explore the problems AI can solve. They'll learn about supervised and unsupervised learning, key ML terminology, and the overall ML process. The day concludes with an introduction to data visualization using Matplotlib.
 Week 4
Lesson 4
Working with Data and Python
This day focuses on handling data in Python. Students will work with Pandas DataFrames and synthetic data, preparing them for their second ML project comparing height and weight data.
 Week 5
Lesson 5
Introduction to Scikit-learn and Linear Regression
Students will finish their height vs. weight comparison project and delve into the crucial role of data in AI. The class will introduce Scikit-learn, a powerful ML library in Python.
 Week 6
Lesson 6
Machine Learning and Linear Regression
Students will work on a prediction project using linear regression to predict study hours and grades deepening their understanding of supervised learning algorithms.
 Week 7
Lesson 7
Nearest Neighbors and Model Evaluation
Students will learn about the Nearest Neighbors algorithm and various distance measurements used in ML. They'll also discover the importance of splitting data into test and training sets and how to evaluate model performance using confusion matrices.
 Week 8
Lesson 8
Working with Real-world Datasets
This session introduces the famous Iris dataset and teaches students how to evaluate datasets. They'll apply their knowledge to a Nearest Neighbors project and learn about loss functions and determining model accuracy.
 Week 9
Lesson 9
Neural Networks and Handwriting Classification
Students will begin an exciting project on handwriting classification using neural networks. They'll learn about the history of neural networks, understand concepts like weights and nodes, and review requirements for their final project.
 Week 10
Lesson 10
Completing Neural Networks Project and Final Review
The final day will be dedicated to completing the neural networks handwriting classification project. Students will further explore loss functions and accuracy determination. The course will conclude with a review of key concepts and final project work.
  • The course will introduce learners to the exciting fields of AI and machine learning. Students will complete 3 projects, using Python and the same tools used by professionals. T
  • he goal of this class is to encourage learners to get excited about the possibilities of AI and ML and ready to continue learning more.
Over 5,000 students from nearly 100 countries across a variety of platforms have started coding in one of my classes. I offer classes covering the foundations of Python and AI. I am the author of the soon-to-be released book All About Python for Kids.  Before teaching, I worked as a software developer for nearly 10 years. I've worked for organizations including Apple, Dell, and Best Buy. I believe the best way to learn is by doing and all my classes are based around hands-on projects that progressively build in difficulty.  I'm a graduate of Mount St. Mary's University in Emmitsburg, Maryland. I can't wait to meet your learner in the class and get started soon. 
수업 외 주당 1 - 2 시간
Homework
빈도: 1-2 per week
피드백: 요청 시 이용 가능
세부 내용: There will be review questions and practice assignments each week, taking approx. 1 to 2 hours. Learners are also strongly encouraged to learn on their own outside of class time. Students will also have an optional final project introduced in week 7 of the class and presented during a optional 3 to 5-minute presentation.
Assessment
빈도: 1-2 throughout the class
세부 내용: All the learners in the last 3 weeks can work on their own machine learning project and complete a optional 3 to 5-minute presentation to the class. Learners will receive feedback from the instructor and other learners for project.
Certificate of Completion
빈도: 1 after class completion
세부 내용: Students will receive a certificate of completion at the end of the class that is fully verifiable online. Students must attend at least 8 classes to receive the certificate.
To succeed in this challenging class, learners need a strong understanding of coding fundamentals including conditional statements, functions, loops, and arrays/lists. Please, read detailed prerequisites included in the class description.
Students will use Google Colab during this class and will need a Google Account to access Colab. Colab is a browser-based code editor and there are no minimum hardware requirements for student computers. Students will need a reliable Windows, Mac, or Linux laptop or desktop for this class. 

*** Intro to AI and ML Class Prerequisites ****

To succeed in this class, learners should have a strong grasp of coding fundamentals.
This includes conditional statements, functions, loops, and arrays/lists. Learners should have completed comprehensive multi-week beginner level coding classes before starting this course. Any programming language is fine, such as Python, Java, JavaScript, C / C++, or Swift. There will be a brief review during the first few classes using Python. There are many excellent beginner Python courses available through Outschool. 
이 수업에서는 아웃스쿨 교실 외에도 다음의 툴을 사용합니다:
Learners will use Google Colab during this class and will need a Google Account to access Colab. Students will also utilize the following Python libraries, including Scikit-learn, NumPy, Matplotlib, Seaborn, and Pandas throughout the class. The documentation (instructions) for these libraries will be used as a reference throughout the course. UC Irvine ML Repository and Kaggle datasets will be used for practice datasets throughout the class. Teachable Machine and ML Playground are low code platforms for machine learning projects. Python.org and W3schools will be used as Python reference sources throughout the class. 

***Intro to AI and ML Class Prerequisites ****
To succeed in this class, learners should have a strong grasp of coding fundamentals 
including conditional statements, functions, loops, and arrays/lists. Learners should have completed comprehensive multi-week beginner level coding classes before starting this course. Any programming language is fine, such as Python, Java, JavaScript, C / C++, or Swift. There will be a brief review during the first few classes using Python. There are many excellent beginner Python courses available through Outschool. 
가입일: April, 2020
4.9
735수강 후기
인기 수업
프로필
교사 전문성 및 자격증
학사 학위 Mount St. Mary's University 부터
With over a decade of coding experience and a passion for education. I have helped over 5,000 students from nearly 100 countries start their coding journey. I offer classes covering the foundations of Python, AI and Machine Learning. I aim to... 
그룹 수업
매주

₩100

또는 10 회 수업에₩350
10주 동안 주당 1회
60분

26 명의 학생이 수업을 완료함
실시간 화상 수업
연령: 12-17
수업당 학습자 6-14 명

아웃스쿨 소개
고객 지원
안전 정책개인 정보CA 개인 정보어린이 개인정보이용 약관
아웃스쿨 홈페이지
앱 다운로드
앱 스토어에서 다운로드Google Play에서 다운로드
© 2024 아웃스쿨