: "From Mathematical Foundations to the Latest Models: Completing the Deep Learning Pipeline with TensorFlow (44 Lectures Total)" The era of simply learning how to call model.fit() is over. From the very foundations of artificial neural networks—differentiation and gradient descent—to the essential use of TensorFlow and Keras in the industry, and even CNN/RNN for handling image and time-series data! We will help you systematically master the entire process of deep learning. Go beyond analyzed data and enter the amazing world of deep learning, where artificial intelligence mimicking the human brain learns and makes decisions on its own.
1 learners are taking this course
Level Basic
Course period Unlimited
A clear understanding of core mathematics for deep learning (calculus, chain rule)
Architecture design capabilities from perceptrons to multi-layer perceptrons (MLP)
Mastering the deep learning model implementation and deployment process using TensorFlow/Keras
Professional model optimization skills using Dropout, EarlyStopping, and Optuna
Basic skills in image and sequence data processing using CNN and RNN
: "From Mathematical Foundations to the Latest Models, Completing the Deep Learning Pipeline with TensorFlow (Total 44 Lectures)"
The era of simply learning how to call model.fit() is over. From the very foundations of artificial neural networks, such as calculus and gradient descent, to the essential use of TensorFlow and Keras in the industry, and even CNN/RNN for handling image and time-series data! We will help you systematically master the entire process of deep learning.
Now, move beyond analyzed data and enter the amazing world of deep learning, where artificial intelligence mimicking the human brain learns and makes decisions on its own.
Key points unique to this lecture
* Solid Mathematical Foundation: We select and easily explain only the essential mathematics for understanding deep learning, from linear/quadratic functions to partial derivatives and the Chain Rule.
* Understanding Deep Learning Architecture: Completely uncover the principles from Single-Layer Perceptrons to Multi-Layer Perceptrons (MLP) and Backpropagation.
* The Pinnacle of Optimization Strategies: We cover everything from Dropout and Early Stopping to prevent overfitting, to how to utilize Optuna, the latest hyperparameter tuning tool.
* Computer Vision & Sequence Data: Covers everything from MNIST image classification (CNN) and time-series/language data processing (RNN) to Transfer Learning for efficient training.
* Real-world Environment Setup: We have included the entire practical process, from setting up a professional development environment using TensorFlow and Keras to model saving and automation.
We will explore the history and fields of application of deep learning, and cover the foundational mathematics (functions, derivatives, partial derivatives, and composite functions) that serve as the engine for neural network learning.
Key Learning: History of Deep Learning, Setting up Development Environment, Basics of Derivatives, Chain Rule
You will learn in-depth about linear regression, the foundation of prediction, as well as gradient descent for finding optimal weights and the principles of the learning rate.
Core Technologies: Hypothesis Function Design, Error Evaluation Metrics, Multiple Linear Regression, Least Squares Method
Understand logistic regression and the sigmoid function, and learn about the structure of the perceptron—the precursor to artificial neural networks—and the multi-layer perceptron that solves the XOR problem.
Key Learning: Sigmoid function, perceptron, solving logic gates, error backpropagation
You will begin designing artificial neural networks in earnest using frameworks. You will create optimal model structures yourself by selecting activation functions and optimizers.
Core Technologies: TensorFlow/Keras usage, activation functions, optimizers, designing basic deep learning structures
Learn core practical techniques for preventing overfitting. You will study Dropout, Early Stopping, automatic model saving, and automated hyperparameter optimization using Optuna.
Key Learning: Checking for Overfitting, Dropout, EarlyStopping, Model Auto-save, Optuna Tuning
Master CNN, the core of image recognition, and RNN for handling sequence data through MNIST practice, and conquer transfer learning to reuse existing models.
Core Technologies: Binary/Multi-class Classification, CNN Architecture, MNIST Practice, RNN Basics, Transfer Learning
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, Samsung Electronics, LG Electronics, SK C&C, and more.
Teaching Fields
I teach 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. I structure my lectures to explain concepts as easily as possible by incorporating my diverse experiences, and I create examples to help students apply them to practice. Since this is not an offline class, please use the Q&A for anything you don't understand.
Who is this course right for?
- For those who want to become a professional deep learning modeler: This is highly recommended for those who want to go beyond simply using libraries and cover everything from the principles (mathematics/theory) of why artificial neural networks work to building practical models all at once.
- For those who want to properly open the 'black box' of deep learning: This is an essential course for aspiring AI engineers who want to gain complete control over the model training process by understanding the core engines of neural networks, such as derivatives, the chain rule, and backpropagation.
- Those who want to push model performance to the limit: Suitable for those struggling with overfitting or those who are desperate for 'real-world' practical techniques to automatically tune hyperparameters using Optuna, a cutting-edge optimization tool.
- For those who want to master image (CNN) and sequence (RNN) data: Recommended for those who want to experience core deep learning architectures, ranging from MNIST digit recognition to time-series data processing and transfer learning, which involves reusing powerful existing models.
- For those who want to master both theory and frameworks (TensorFlow/Keras) simultaneously: This was prepared for those who are curious about how to implement complex formulas into code and how to integrate TensorFlow's powerful features into real-world projects.
Need to know before starting?
Basic knowledge of Python syntax, Numpy, and Pandas is required.
Even if you lack a mathematical background, the core concepts are covered within the lectures, so you can successfully complete the course as long as you have the passion.
16,019
Learners
826
Reviews
594
Answers
4.7
Rating
44
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.
All
44 lectures ∙ (15hr 27min)
Check out other courses by the instructor!
Explore other courses in the same field!
Limited time deal
$27,500.00
50%
$42.90
![[ICT Archive] Big Data Core and Business ModelsCourse Thumbnail](https://cdn.inflearn.com/public/files/courses/338811/cover/01k44rs7zkwq0ehc8vqsy2mdtb?w=420)
![[7-Day Complete] Pass MS AI-900 Certification in One GoCourse Thumbnail](https://cdn.inflearn.com/public/files/courses/338854/cover/01k4caartf5v7x2e574pq0wnp8?w=420)
