[비디오이미지프로세싱] 01~17. 목차

 

 

week1

Lecture 1

• Syllabus
• Course Overview

Lecture 2 

• Machine Learning / Deep Learning for
• Image Processing and Computer Vision

Lecture 3

• Linear Regression
• Gradient Descent

Lecture 4

• Tutorials of
  Python and necessary libraries

 

week2

Lecture 5

•Gradient Descent (GD) Continued
• Stochastic Gradient Descent (SGD)

Lecture 6

• Traditional Classification Methods
• K-Nearest Neighbors (KNN)

Lecture 7

• Tutorials of
   Linear Regression

 

week3

Lecture 8

• Traditional Classification Methods
• K-Nearest Neighbors (KNN) continued
• Validation sets: hyperparameter tuning

Lecture 9

• Traditional Classification Methods
• Support Vector Machine (SVM)

Lecture 10

• Tutorials of 
  k-nearest neighbors (kNN)
• Image Classification
• Cross Validation

 

week4

Lecture 11

• Traditional Unsupervised Learning
• Clustering method: k-means

Lecture 12

• Traditional Unsupervised Learning
• Principal Component Analysis (PCA)
• :Dimensionality Reduction

Lecture 13

• Tutorials of
  kMeans (Image Segmentation)

 

week6

Lecture 14 

• Recap: Linear Classification
• Loss Function & Optimization
• Regularization
• Overfitting & Underfitting
• Optimization

Lecture 15

•Neural Networks
• Introduction
• Backpropagation

Lecture 16

•Introduction to Deep Learning
• Recap:
   • Computational Graph
   • Backpropagation
• Brief History
   • Types of Layers
   • Fully Connected (FC), Convolution, Pooling, Softmax…

 

week7

Lecture 17

•Introduction to Deep Learning Continued..
• Layers in Convolutional Neural Networks

 

---

참고문헌

 

나의 첫 머신러닝/딥러닝

파이썬으로 구현해보는 필수 머신러닝/딥러닝 알고리즘

• 저자
  허민석
• 출판
  위키북스
• 출간
  2019.01.10.

 

밑바닥부터 시작하는 딥러닝

파이썬으로 익히는 딥러닝 이론과 구현

• 저자
  사이토 고키
• 번역
  개앞맵시(이복연)
• 출판
  한빛미디어
• 출간
  2017.01.03.

 

모두의 딥러닝

원리를 쉽게 이해하고 나만의 딥러닝 모델을 만들 수 있다!

• 저자
  조태호
• 출판
  길벗
• 출간
  2017.12.27.