inflearn logo

AI Development Part 5: Practical Deep Learning Projects

: "From environment setup to 7 practical projects, a deep learning full-stack journey across data domains (35 lectures in total)" Go beyond simply following example code and learn how to cook various types of real-world data using deep learning. Starting from building CPU/GPU development environments, you will cover waste sorting classification (Image), stock price prediction (Time-series), ECG anomaly detection (AE), animation stylization (GAN), medical image segmentation (U-Net), and sound classification (Audio)! Systematically master core deep learning algorithms through hands-on projects.

5 learners are taking this course

Level Basic

Course period Unlimited

AI
AI
Deep Learning(DL)
Deep Learning(DL)
Machine Learning(ML)
Machine Learning(ML)
Python
Python
Big Data
Big Data
AI
AI
Deep Learning(DL)
Deep Learning(DL)
Machine Learning(ML)
Machine Learning(ML)
Python
Python
Big Data
Big Data

What you will gain after the course

  • * Ability to build a deep learning development environment utilizing CPU/GPU hardware acceleration

  • * More than 5 data preprocessing techniques for images, time series, sound, biosignals, etc.

  • * Practical implementation skills for core deep learning models such as LSTM, GAN, AE, and U-Net

  • * Ability to design integrated services combining OpenCV and deep learning models

  • * Know-how for maximizing model performance using Transfer Learning

Course Introduction

: "From environment setup to 7 practical projects, a full-stack deep learning journey across data domains (35 lectures in total)"

Beyond simply following example code, you will learn how to cook up various types of real-world data using deep learning. Starting from setting up CPU/GPU development environments, you will systematically master core deep learning algorithms through practical projects, including waste sorting classification (Image), stock price prediction (Time Series), ECG anomaly detection (AE), animation stylization (GAN), medical image segmentation (U-Net), and sound classification (Audio)!

 

Key points unique to this course

* Overwhelming Project Variety: Beyond image classification, we cover all key industry domains, including time series, audio, generative models, and medical imaging.

* Practical Environment Setup: We show you everything from setting up a GPU environment—an essential gateway to deep learning—to real-world data preprocessing steps without omission.

* Hands-on practice with the latest architectures: Directly implement and apply optimal models for specific purposes, such as LSTM, AutoEncoder, CycleGAN, and U-Net.

* Unstructured Data Master: Directly handle challenging data types such as Mel-spectrograms (sound), DICOM-based medical images, and time-series stock price data.

* Integration with OpenCV: Combine deep learning models with OpenCV to design pipelines at a level applicable to real-world services.

You can check it by visiting the Soft Campus website, which offers various content services and discounts.

http://www.softcampus.co.kr/main.softcampus


 

📱 Curriculum & Project Preview


✒ Section 1. Starting Deep Learning and Setting Up the Environment (Lecture 1 ~ Lecture 3)

Before diving into the actual learning, you will understand the flow of deep learning and perfectly set up CPU and GPU development environments to maximize learning speed.

Key Learning: Course roadmap, local and cloud GPU environment setup


✒Section 2. [Project 1] Smart Waste Sorting Classifier (Lecture 4 ~ 9)

Experience the entire process of image classification. You will learn everything from data collection and preprocessing to implementing high-performance models using Transfer Learning.

Core Technologies: Image data preprocessing, data augmentation, CNN, transfer learning utilization strategies

 

✒ Section 3. [Project 2] Time Series Stock Price Data Analysis (Lectures 10 ~ 12)

You will learn how to process time-varying data using Samsung Electronics stock price data. You will derive insights through EDA and apply recurrent neural networks.

Core Technologies: Time-series data EDA, Data normalization, LSTM (Long Short-Term Memory) modeling


✒ Section 4. [Project 3] ECG Data Anomaly Detection (Lessons 13 ~ 16)

Distinguish between normal and abnormal states using bio-signal data. Learn the principles of AutoEncoder, a leading unsupervised learning technique, and how to apply it in practice.

Key Learning: ECG data characteristics, AutoEncoder (AE) overview and implementation, anomaly detection logic


✒ Section 5. [Project 4] Animating Photos Using GAN (Lecture 17 ~ Lecture 23)

We cover the most exciting field of Generative AI. We will take a deep dive into the CycleGAN architecture, which transforms ordinary photos into animation styles.

Core Technologies: Principles of GAN, Image-to-Image Translation, CycleGAN Architecture and Application


✒ Section 6. [Project 5] Medical Image-Based Disease Diagnosis (Lectures 24 ~ 28)

Learn image segmentation, the core of medical AI. Acquire the technology to accurately locate specific disease areas within images using the U-Net model.

Core Technologies: U-Net Architecture, Medical Image Preprocessing, Semantic Segmentation


✒ Section 7. [Project 6] Sound Data Classification (Lessons 29 ~ 32)

Convert sound data into a form that deep learning can understand and classify it. Learn the libraries and techniques essential for audio processing.

Key Learning: Utilizing Librosa, Mel Spectrogram conversion, and audio deep learning modeling


✒ Section 8.[Project 7] Total Number Calculator (Lecture 33 ~ Lecture 35)

This is an integrated project combining OpenCV and deep learning. You will complete a practical pipeline that recognizes numbers from images and performs physical calculations.

Key Learning: OpenCV image processing, deep learning model integration, digit recognition, and total sum calculation logic


✒ Introduction to Knowledge Sharer

Jaesung Yoon (Lead Instructor for Data Analysis at Like Lion)


Development Experience
• Developed and launched SKT "Island Adventure" mobile content
• Developed and launched KT "Quiz Soccer" mobile content
• Launched SK "Mobile Real Estate Agent"
• Developed iPhone "Hanjatong" app
• Developed iPhone "Health Training" app
• Developed KT/SK Japanese Namco "Tales of Commons" content
• Developed KT mini-games (Yageum Yageum Land Grab, Aladdin's Magic Lamp, Mystery Block Detective Agency, BUZZ and BUZZ)

Teaching Experience
A veteran instructor with 19 years of experience in teaching and development for current employees of famous domestic companies and job seekers, including Samsung Multi Campus, Busan IT Industry Promotion Agency, Jeonju IT & Cultural Industry Promotion Agency, Incheon IT Industry Promotion Agency, Korea Radio Promotion Association, SK C&C, T Academy, Korea Institute for Robot Industry Advancement, Daejeon ETRI, Samsung Electronics, nica Education Center, Korea Productivity Center, Hanwha S&C, LG Electronics, and more.

Teaching Fields
Teaches in fields such as Java, Android, Frameworks, Databases, UML, iPhone, Big Data processing and analysis, Python, IoT, data analysis using R/Python, Deep Learning, Machine Learning AI, and Spark. The courses are structured to explain concepts as easily as possible by incorporating diverse experiences, and to create examples that allow students to apply them to practice. Since this is not an offline class, please use the Q&A for anything you don't understand.

Recommended for
these people

Who is this course right for?

  • * For those who want to learn quickly through projects: For those who want to build multiple functional AI models rather than going through tedious lists of theories.

  • * Those who want to experience various data domains: Those who want to master all types of unstructured data, including not only images but also time-series, audio, and medical data.

  • * For those curious about Generative AI and the latest architectures: Those who want to directly implement models gaining attention in the field, such as GAN, CycleGAN, and U-Net.

  • * Job seekers/career changers who need a portfolio: Those who want to secure 7 deep learning project results that are not limited to a single field.

Need to know before starting?

  • You should be familiar with basic Python syntax, and it is best if you have experience with basic data handling using Numpy and Pandas.

  • It focuses on practical implementation and application rather than the mathematical principles of deep learning models, so beginners with coding skills will be able to follow along easily.

Hello
This is softcampus

16,075

Learners

827

Reviews

594

Answers

4.7

Rating

45

Courses

Soft Campus is an education center that supports online and offline lectures and content sales.

For inquiries regarding AI-related fields and the purchase of various lectures and content, please contact us at raputa@nate.com or by phone at 02-553-0824.

Thank you.

More

Curriculum

All

37 lectures ∙ (12hr 31min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

Not enough reviews.
Please write a valuable review that helps everyone!

softcampus's other courses

Check out other courses by the instructor!

Similar courses

Explore other courses in the same field!

Limited time deal

$49,500.00

50%

$77.00