딥러닝 CNN 완벽 가이드 - Pytorch 버전
권 철민
딥러닝·CNN 핵심 이론부터 다양한 CNN 모델 구현 방법, 실전 문제를 통한 실무 딥러닝 개발 노하우까지, Pytorch 기반의 딥러닝 CNN 기술 전문가로 거듭나고 싶다면 이 강의와 함께하세요 :)
초급
딥러닝, PyTorch, 컴퓨터 비전
If you want to be recognized as a machine learning expert based on large-scale data, from understanding the core framework of Spark machine learning, to SQL-based data processing through difficult practical problems, to data analysis through business domain analysis, and to the ability to implement optimized machine learning models, please join this course.
937 learners

Implementing Machine Learning Models in Spark
Detailed understanding of DataFrame, the foundation of Spark's data processing
Understand the various technical elements that make up the Spark Machine Learning Framework
Mastering Spark's Machine Learning Pipeline
Ability to use SQL for data analysis
SQL-based Feature Engineering Techniques
Implementing models with XGBoost and LightGBM in Spark
Model hyperparameter tuning method based on Bayesian optimization
Improve your data analysis and ML model implementation skills simultaneously through challenging real-world problems.
Data analysis method based on analysis domain
Various data visualization techniques
Data analysis + feature engineering + ML implementation,
master all three skills at once.
The ultimate open source large-scale distributed processing solution Apache Spark meets Machine Learning.
Many large corporations and financial institutions in Korea are using Apache Spark to analyze big data and create machine learning models. Since Spark is based on a distributed data processing framework, it can process large volumes of data and create ML models by scaling capacity across anywhere from a few to dozens of servers. This allows us to overcome the limitations of scikit-learn, which can only implement machine learning models on a single server.
The 'Spark Machine Learning Complete Guide - Part 1' course will help you grow into a machine learning expert skilled in data processing and analysis, going beyond just learning how to implement machine learning models in Spark.
To grow into a true machine learning expert, it's crucial to develop not only ML implementation skills but also the ability to process and combine business data to create ML models. For this purpose, you will learn through hands-on practice how to process data using SQL, which is most widely used for handling large-scale data in real-world applications, and data analysis techniques based on business domain analysis.
Implementing machine learning models on a Spark foundation is not easy. This is because you encounter many problems that existing data scientists or machine learning experts have never experienced before, such as unique machine learning APIs and frameworks based on Spark architecture's special characteristics, and SQL-based data processing.
Through this course, Spark Machine Learning Complete Guide, I will help you develop the ability to solve the problems you encounter.
The first half of the course consists of detailed theoretical explanations and abundant hands-on practice covering various components that make up the Spark Machine Learning Framework, including DataFrame, SQL, Estimator, Transformer, Pipeline, Evaluator, and more. Through this, you will be able to implement ML models in Spark easily and quickly.
Additionally, I will provide detailed explanations on how to use XGBoost and LightGBM in Spark, and how to tune hyperparameters using HyperOpt based on Bayesian optimization.
The latter part of the course will enhance both your practical data processing/analysis skills and machine learning model implementation abilities through hands-on practice with Kaggle's Instacart Market Basket Analysis competition. The Kaggle Instacart competition is a high-difficulty competition, and the dataset is particularly composed of e-commerce order processing tables (products, orders, order products).
Through this dataset, you will learn in detail how to process and analyze business data based on SQL and perform Feature Engineering, how to derive analysis domains in business contexts, and how to create models based on the features derived in this way.
The 'Complete Guide to Spark Machine Learning' course being released this time is Part 1. The Part 2 course is scheduled to be released later and will cover text analysis, recommendation, and time series analysis.
💻 Please check before taking the course!
The hands-on practice uses Databricks. Databricks provides a notebook environment where you can create Spark-based applications in the cloud without installing Spark.
We will provide detailed information about the practical training costs when using Databricks Free Edition after testing until the end of November 2025.
You can download the lecture practice code and lecture explanation materials from 'Download Practice Code and Explanation Materials'.
This course is designed assuming that students have knowledge of Chapter 5 (Regression) from the Python Machine Learning Complete Guide or equivalent knowledge, and also have understanding of very basic aspects of SQL. Please refer to the above requirements when selecting this course.
It would be good if you know the basics of Spark, but even if you don't, you shouldn't have any problems following the course.
Curious about the knowledge creator's interview? (Click)
Who is this course right for?
Anyone who wants to implement machine learning using Spark
Those who want to implement machine learning based on large-scale data
Anyone who wants to improve their data processing techniques for machine learning using SQL
Anyone who wants to learn the entire process of processing data into the desired format and creating an ML model based on it in practice
Anyone who wants to improve data analysis, feature engineering capabilities, and ML implementation
Need to know before starting?
Understanding up to Chapter 5 (Regression) of the Complete Guide to Python Machine Learning or equivalent prior knowledge
Understanding SQL Basics
26,923
Learners
1,367
Reviews
4,010
Answers
4.9
Rating
14
Courses
(전) 엔코아 컨설팅
(전) 한국 오라클
AI 프리랜서 컨설턴트
파이썬 머신러닝 완벽 가이드 저자
All
122 lectures ∙ (24hr 53min)
Course Materials:
All
28 reviews
4.9
28 reviews
Reviews 7
∙
Average Rating 5.0
5
파이썬 머신러닝 완벽가이드 통해서 권철민선생님을 처음 알게 되었습니다. 그 강의를 통해서 비전공자였던 저는 포기하려고 했던 이 분야를 포기하지 않을 수 있었습니다. 현재 이 분야에서 일을 하면서 이렇게 인프런 강의를 들으며 공부도 꾸준히 하고 있습니다. 선생님께 감사하다는 말씀을 전하고 싶어서 처음에 질문답변 사안에 선생님께 감사하다는 말씀을 드렸었는데, 선생님께서 꾸준히 하면 노력한 바를 이룰 수 있을 거라고 응원하면서 말씀해주셨습니다. 앞으로도 선생님께서 강의하시는 것 꾸준히 들을 예정입니다. ^^ㅎㅎ 그만큼 정말 잘 가르쳐주십니다. 권철민 선생님 이 자리를 빌러, 진심으로 정말 감사합니다.
이렇게 가슴 뭉클한 수강평을 남겨 주시다니 제가 더 감명 받았습니다. 강의를 만드는 수고를 한 순간에 보상받는 글이여서 제가 오히려 감사드려야 할 것 같습니다. 앞으로도 계속 이렇게 정진하신다면, 원하는 모든 일 확실히 다 성취 하실 것입니다. 감사합니다.
Reviews 54
∙
Average Rating 5.0
Reviews 13
∙
Average Rating 5.0
Reviews 8
∙
Average Rating 4.9
Reviews 1
∙
Average Rating 5.0
Limited time deal ends in 07:20:31
$74,250.00
25%
$77.00
Check out other courses by the instructor!
Explore other courses in the same field!