TUTORIALS

Note: Lecture slides are best viewed in Chrome.

 

[대한금속·재료학회] 인공지능재료과학 분과 2020 하계단기강좌 “딥러닝의 기초이론과 재료설계 및 공정 최적화에 응용”   [YouTube]

Dates Topics Jupyter notebook Slides
07/01/20 Python Installation
Docker Installation (optional)
iNote#00_1
iNote#00_2
Introduction pdf#00
Linear Algebra iNote#01 pdf#01
Optimization and Gradient Descent iNote#02 pdf#02
Regression iNote#03 pdf#03
Classification iNote#04 pdf#04
07/02/20 Artificial Neural Networks iNote#05 pdf#05
Autoencoder iNote#06 pdf#06
Convolutional Neural Networks (CNN) iNote#07 pdf#07
Generative Adversarial Networks (GAN) iNote#08 pdf#08

 

[한국소음진동공학회] E-Conference Tutorial 강연   [YouTube]

Dates Topics Jupyter notebook Slides
Docker Installation iNote#00
Introduction pdf#01
신호처리 (FFT and STFT) iNote#02 pdf#02
진동, 열, 음향신호 분석을 위한 합성곱 신경망 (CNN) iNote#03 pdf#03
설명가능한 인공지능 (CAM) iNote#04 pdf#04
진동신호 분석을 위한 순환 신경망 (RNN) iNote#05 pdf#05
진동신호 생성을 위한 적대적 생성 신경망 (GAN) iNote#06 pdf#06

 
[internoise2020] Deep Learning for Noise/Vibration Engineering

Deep learning, considered as one of the breakthrough technologies in machine learning in recent years, has attracted tremendous research attention in both academia and industrial communities. It involves learning good representations of data through multiple levels of abstraction and can discover complicated underlying structures and features, thus achieving improved predictive performance. As a result, the noise and vibration community also starts to apply deep learning technologies to their applications. In this tutorial, I will first provide an overview of deep learning technology including ANN, CNN, RNN, and Autoencoder. In particular, the basic python codes with the TensorFlow library will be shared and explained during the tutorial. This tutorial can help more researchers in this community to understand the philosophy of deep learning and to utilize the provided codes in their practices. Ultimately I hope this tutorial can stimulate more research interests towards deep learning technology within our community.

– Deep learning (ANN, CNN, RNN, Autoencoder)
– Demo with vibration data from rotating machinery
– Python codes with TensorFlow will be provided.

Dates Topics Jupyter notebook Slides Files or Data
08/23/20 Python Installation
Linear Algebra iNote#01 pdf#01
Optimization and Gradient Descent iNote#02 pdf#02
Regression iNote#03_1
iNote#03_2
pdf#03
Classification: Perceptron
Classification: SVM
Classification: Logistic Regression
iNote#04
iNote#05
iNote#06
pdf#04
pdf#05
pdf#06
Artificial Neural Networks iNote#07 pdf#07
Autoencoder iNote#08 pdf#08
Convolutional Neural Networks (CNN) iNote#09 pdf#09
Generative Adversarial Networks (GAN) iNote#10 pdf#10