AI를 위한 딥러닝
- 중앙대학교
- 곽일엽
페이스북
트위터
카카오톡
네이버밴드
링크복사
-
- 주제분류
- 자연과학 >수학ㆍ물리ㆍ천문ㆍ지리 >통계학
-
- 강의학기
- 2022년 1학기
-
- 조회수
- 10,484
-
- 강의계획서
- 강의계획서
딥러닝 기초를 강의합니다. Tensorflow 와 keras 를 학습합니다. 기본적인 딥러닝 개념들 학습 후, 간단한 computer vision, timeseries, text 분석방법에 대해 공부해 봅니다. François Chollet 의 Deep Learning with Python 2판을 사용합니다.
- 수강안내 및 수강신청
- ※ 수강확인증 발급을 위해서는 수강신청이 필요합니다
Introduction to github, Markdown, Jupyter notebook
차시별 강의
| 1. | |
Introduction to github, Markdown, Jupyter notebook | Introduction to colab and github |  |
|
Introduction to github, Markdown, Jupyter notebook | Intro to Markdown | |
|
|
Ch1 What is deep learning | Key factors behind deep learning’s rising popularity and future potential | |
|
| 2. | |
Ch2 The mathematical building blocks of neural networks (1) | A first example of a neural network | |
|
Ch2 The mathematical building blocks of neural networks (2) | Tensors and tensor operations | |
|
| 3. | |
Ch2 The mathematical building blocks of neural networks (3) | How neural networks learn via backpropagation and gradient descent | |
|
Ch3 Introduction to Keras and TensorFlow | A closer look at TensorFlow, Keras, and their relationship | |
|
| 4. | |
Ch4 Getting started with neural networks: Classification and regression | first examples of real-world machine learning workflows - classification and regression examples | |
| 5. | |
Ch5 Fundamentals of machine learning | Understanding the tension between generalization and optimization, the fundamental issue in machine learning | |
|
Ch6 The universal workflowof machine learning | Steps fframing a machine learning problem, Steps fdeveloping a working model | |
|
| 6. | |
Ch7 Working with Keras: A deep dive | Creating Keras models, Using built-in Keras training and evaluation loops, Using Keras callbacks | |
| 7. | |
Ch8 Introduction to deep learning for computer vision | Understanding convolutional neural networks, Using data augmentation, Using a pretrained convnet, Fine-tuning a pretrained convnet | |
| 8. | |
Ch9 Advanced deep learning for computer vision (1) | The different branches of computer vision, Modern convnet architecture patterns | |
| 9. | |
Ch9 Advanced deep learning for computer vision (2) | Techniques for visualizing and interpreting what convnets learn | |
|
Ch10 Deep learning for timeseries | Examples of machine learning tasks that involve timeseries data, Understanding recurrent neural networks, Advanced RNN | |
|
| 10. | |
Ch11 Deep learning for text (1) | Preprocessing text data for machine learning applications, Bag-of-words approaches and sequence-modeling approaches for text processing | |
| 11. | |
Ch11 Deep learning for text (2) | The Transformer architecture, Sequence-to-sequence learning | |
| 12. | |
Ch12 Generative deep learning | text generation, deep dream | |
연관 자료
