강의

멘토링

커뮤니티

NEW
AI Technology

/

Deep Learning & Machine Learning

(First Steps in Deep Learning Modeling) Master the Core Theory of Deep Learning from Gradient Descent to Backpropagation with Formulas and Code!

Based on over 100 deep learning training sessions, this course systematically organizes the core foundational theories that students found most challenging. The course connects mathematical intuition, model learning principles, and code implementation step by step in a way that even non-majors can understand, deeply covering the fundamental structure and operating principles of how AI models learn, rather than just library usage. This is a practical introductory course designed to help you grow into a skilled engineer who understands AI principles by implementing core deep learning foundational technologies such as gradient descent, loss functions, optimization, perceptrons, multilayer neural networks, and backpropagation through both formulas and code.

6 learners are taking this course

  • fasoft
딥러닝입문
딥러닝기초
Tensorflow
경사하강법
딥러닝모델
Python
AI
Numpy
Deep Learning(DL)

What you will gain after the course

  • Establishing a theoretical foundation to independently explain the principles of deep learning

  • Practical coding skills to implement models directly with Numpy and TensorFlow

  • AI Development Environment Setup and Hands-on Skills

  • Experience creating a 'prediction model' using real data

  • # Functional Understanding of Neural Network Architecture and Backpropagation

  • Understanding the Mathematical Concepts Behind Gradient Descent and Error


From AI Principles
to Code Implementation



Are you stuck just following library code? You've been curious about the fundamental principles of why deep learning models learn and how loss functions decrease, haven't you?

The AI engineers that companies want in the field are not simply people who execute code, but those who understand AI principles and solve problems on their own.
I've included insights gained from teaching over 100 lectures.

Build a solid foundation in deep learning by implementing formulas and code yourself, an opportunity to elevate your capabilities as an AI developer to the next level.



What You'll Learn from This Course

Master the fundamental principles of AI models through equations and code.

The path to becoming 'an engineer who understands AI principles' as required in the field - with over 100 lectures of experience, I'll help you build the foundation from the ground up for the most challenging basic theories. From mathematical intuition to code implementation, explained step by step in a connected manner.

Beyond simple library usage, this course provides an in-depth exploration into the fundamental structure and operating principles of how AI models learn. It's an opportunity to gain solid understanding by directly implementing complex deep learning theories.

You'll master AI principles by implementing core foundational techniques such as gradient descent, loss functions, optimization, perceptrons, and backpropagation through both mathematical formulas and code. I'll help you grow into a capable engineer who can design models and solve problems independently.

Grow as an engineer who understands the core principles of AI.
I will take full responsibility for ensuring you have a solid understanding of the 'fundamental principles' that form the foundation of all AI learning.


Real AI Engineering
Born from Field Experience


As a programmer, I always delved into the principles of AI models in the field.

Beyond simply using libraries, I asked fundamental questions about how models learn and why loss values don't decrease.

However, practice often differed from theory.

I experienced countless trials and errors while working with real data.

So I decided to create a course that penetrates the core of AI without getting lost between complex formulas and code.

Now you're ready to take your AI capabilities to the next level based on that experience.


Become an engineer who clearly understands how AI works and solves problems independently.
Now, let's move forward together as AI experts with solid fundamentals.



Curriculum

Deep Learning Modeling Core Mastery

Section 1

AI Basic Concepts and Modeling Understanding

This course emphasizes the importance of AI learning principles and introduces the competencies required of AI engineers in the field. It clarifies the fundamental concepts of deep learning modeling and the differences from rule-based programming, covering AI history, research areas, and core foundational technologies. Additionally, it builds the foundation of AI modeling through development environment setup and hands-on practice.

Section 2

Learning Regression Analysis and Mathematical Concepts

Clearly organize the basic concepts of regression analysis and statistical terminology, and learn how to find the optimal prediction line through linear regression models. Understand the principles of the least squares method and implement it in code, then expand from the limitations of least squares to gradient descent, a core principle of deep learning. Deepen your understanding of gradient descent using derivatives.

Section 3

Advanced Gradient Descent Practice

We manually implement gradient descent and practice with NumPy-based code to develop practical application skills. We implement the process of finding the intercept using gradient descent with errors and gradients in code, understand the importance of the learning rate, and apply it in detail to the gradient descent code.

Section 4

Advanced NumPy and TensorFlow Basics

You will learn advanced NumPy content to understand TensorFlow. This covers how to predict values through AI models, basic concepts of TensorFlow, and differences between versions. It addresses TensorFlow data types, basic code practice and gradient descent implementation, how to use random functions, and the importance of learning rate.

Section 5

Machine Learning Workflow and TensorFlow in Practice

Systematically understand machine learning and deep learning workflows. Deepen your understanding of gradient descent implementation theory and practice based on TensorFlow 2.x, and develop the ability to visually analyze the model training process through environment setup and hands-on practice using TensorBoard.

Section 6

Linear and Multiple Regression Practical Modeling

Conceptually understand and implement a multiple linear regression model using TensorFlow. Learn how to read actual data files using NumPy, and develop the ability to verify and interpret results through graphs via data-driven multiple linear regression theory and practice.

Section 7

Classification Models, Neural Networks, and Backpropagation

Learn how to solve classification problems through logistic regression and understand the principles of loss functions and optimizers. Identify the limitations of single perceptrons and solve the XOR problem with multi-layer perceptrons, while exploring the structure and principles of neural networks in depth. Finally, learn the theory and practical application of backpropagation.




Recommended Audience

This is recommended for the following people

AI Principles: A Guide for Frustrated Beginner Developers

Non-majors who are afraid of formulas/code




Pre-enrollment Notes


Practice Environment

  • A Python 3.x version environment is required.

  • TensorFlow and NumPy library installation is required.

  • The operating system can be Windows, macOS, or Linux.

  • GPU usage can help improve training speed.

Prerequisites and Important Notes

  • Basic knowledge of Python programming is required.

  • Having a basic understanding of linear algebra and calculus concepts will make it easier to understand.

  • It's okay if you don't have experience with deep learning frameworks.

  • Since it covers mathematical principles in depth, consistent review is important.

Learning Materials

  • The practice code is provided in Jupyter Notebook or Google Colab environment.

  • I will provide additional reference material links related to the lecture content.


Recommended for
these people

Who is this course right for?

  • A beginner AI developer who just follows libraries but gets stuck every time because they don't understand the principles

  • Those who feel frustrated because they don't understand why models learn or why loss doesn't decrease, and can't solve problems on their own once they move beyond tutorials

  • Non-CS majors who want to start deep learning but are hesitant to take the first step due to fear of mathematical formulas and code

  • Data analysts who know how to preprocess and prepare data but are weak in 'modeling principles' and always depend on developers

  • Learners who know basic TensorFlow syntax but have never implemented gradient descent, optimizers, and backpropagation in actual code

  • Developers who don't understand the various options in deep learning modeling code

Need to know before starting?

  • Python Basic Grammar

Hello
This is

39

Learners

4

Reviews

5.0

Rating

3

Courses

인공지능, 데이터분석, 스마트 팩토리, 로봇제어, C언어, 파이썬에 대한 풍부한 현장 경험을 바탕으로 그 누구보다 쉽게 가르치는 방법을 늘 연구하고 노력하는 프로그래머입니다.

수많은 강의를 통해 늘 최고의 강의 평점으로 검증된 강사라고 자부합니다.

Curriculum

All

30 lectures ∙ (11hr 1min)

Published: 
Last updated: 

Reviews

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

Limited time deal

$506,680.00

68%

$59.40

fasoft's other courses

Check out other courses by the instructor!

Similar courses

Explore other courses in the same field!