Introduction
Do you remember AlphaGo? It is the first thinking machine to defeat a human champion in Go. In this class, we are going to explore the unknown world of machine learning, the technology that implements artificial intelligence.
Covers the fundamentals of machine learning, including:
Supervised and unsupervised learning algorithms
Regression, classification, and clustering
Model evaluation, feature selection, and regularization
Teaches algorithms such as:
Linear and logistic regression
Naive Bayes, decision trees, random forests, and kNN
K-means and Apriori
Covers advanced topics like natural language processing
Uses R for implementation and practical projects
By the end of the course, students will have a strong understanding of the basics of machine learning.
Modern academic area helping people to draw useful information and intuition so that making them to make reasonable decisions
Steps in Data Science project
Understanding the business problem (문제 인식)
Data acquisition (데이터 수집)
Data preparation (데이터 전처리)
Exploratory data analysis (탐색적 분석 → 가설)
Data modeling (모델링 → 가설 검증 → 예측)
Visualization and communication (시각화를 통한 소통)
Deploy & maintenance (지속적인 피드백을 통한 모델 보완)
Requirement
AI, ML, and Deep Learning
Artificial intelligence, machine learning, deep learning; these terms appear a lot in newspapers and books these days, right? Let’s summarize it first.
Machine learning
, which we will learn in this class, is, as already mentioned, that a machine learns from data to create a model and predict new situations.
Deep learning
is one of many techniques of machine learning.
Have you ever heard of artificial neural networks? Deep learning is one of the machine learning techniques that uses artificial neural networks.
AlphaGo, mentioned above, is also a machine learning technology that applies deep learning. In other words, deep learning exists within machine learning.
Deep learning learns large amounts of data through artificial neural networks.
Artificial intelligence
is a technology that allows machines to mimic human behavior.
After all, all of these technologies are meant to help people make decisions and act.
AI, ML, and Deep Learning
ChatGPT
is a part of the field of Machine Learning, specifically the subfield of Natural Language Processing (NLP).
In NLP, language models are used to generate text that is semantically and contextually appropriate given a prompt.
ChatGPT is a specific type of language model that is fine-tuned on a large corpus of conversational text, making it particularly well-suited for tasks such as generating responses in a chatbot or answering questions.
The transformer architecture and the large number of parameters in ChatGPT allow it to capture long-range dependencies between the input and output, making it capable of generating coherent and contextually appropriate text even when the prompt is very long.
When you think of artificial intelligence, some people immediately think of Terminator or Ultron. You don’t have to be afraid.
Because, a cute robot like below is enough to help our thought
“Any sufficiently advanced technology is indistinguishable from magic” Arthur C. Clarke
Arthur Clark, now deceased science fiction writer, said this.
Things that only appeared in sci-fi movies when I was a kid are already happening.
With the development of the Internet and communications, truly magical things are already happening.
You now carry a supercomputer in your hand, right? (I mean, your smartphone!)
For me in the past, people who use smartphones today are almost wizards.
This is one of the things I am somewhat certain of: In the near future, programs called data science now will be used as easily as Excel, and machine learning will be used as widely as those using smartphones today, and anyone can use it.
Let’s learn magic a little earlier than others.
Pre-class
Prior to attending the offline (or online streaming Zoom class), students are expected to view the recorded lecture delivered by the lecturer.
They are encouraged to take an active role in their learning by studying the material independently.
The video covers the fundamental concepts of the Machine Learning algorithm, including its underlying theory when necessary.
To assess their level of understanding, students are required to submit discussion posts. This serves as a means for evaluating their comprehension of the material.
In-class
During the class, the lecturer will summarize the pre-class lecture and provide additional clarification on the concepts covered.
To reinforce their understanding, students will engage in hands-on practice with more advanced code. This will provide them with the opportunity to apply their knowledge and develop their coding skills.
The official in-class time is 9:00 ~ 10:50
See the About section in course home
Items | Ratio (%) |
---|---|
Attendance | 0 |
Discussion Submission | 20 |
QZ #1 & QZ #2 | 40 |
PBL Proj Final Score | 40 |
Total | 100 |
When attendance falls below 1/3 in a class, it may result in a grade of F
The Final Score for the PBL is calculated by multiplying the PBL Team Score with the Individual Peer Review Score.
Individual Peer Review Scores are obtained through an anonymous survey conducted within the group.
Data in use will be guided but not limited to them, Team can use their own data
Please join Kakao open-chat room
When you enter, please make sure to enter your name as it is on the attendance sheet. (입장하셔서 이름을 꼭 출석부에 있는 이름으로 설정해주세요.)
CJ-counselling room (Anything but the class content)