- ์ ์ฒด๋ณด๊ธฐ(24)
- Deep Learning(11)
- DL(11)
- ์ธ๊ณต์ง๋ฅ(11)
- ML(11)
- Computer Vision(10)
- ๋ ผ๋ฌธ๋ฆฌ๋ทฐ(10)
- ์ปดํจํฐ๋น์ (10)
- EECS(10)
- cs231n(10)
- ์คํ ํฌ๋ ๋ฅ๋ฌ๋(10)
- ๋ฏธ์๊ฐ ๋ฅ๋ฌ๋(10)
- ๋ฅ๋ฌ๋(5)
- ์๊ณ์ด(5)
- michigan(5)
- michigan ๋ฅ๋ฌ๋(5)
- pcb ๊ฒฐํจํ์ง(4)
- PCB(4)
- pcb defect detection(4)
- Time Series(4)
- defect detection(4)
- forecasting(3)
- ์๊ณ์ด ์์ธก(3)
- AAAI(3)
- ๋ค์ด๋๋ฏนํ๋ก๊ทธ๋๋ฐ(2)
- self-attention(2)
- transformer(2)
- ํ์ด์ฌ(2)
- ์๊ณ ๋ฆฌ์ฆ(2)
- AAAI 2023(2)
- DP(2)
- RNN(1)
- machine learning(1)
- loss function(1)
- Greykite(1)
- ์ดํ ์ (1)
- ํธ๋์คํฌ๋จธ(1)
- Image Anomaly Detection(1)
- ์ด๋ฏธ์ง ์ด์ ํ์ง(1)
- Outlier Impact(1)
- ์๋ฒ ์ด(1)
- 2021(1)
- DeepStream(1)
- NIPS(1)
- Masked Autoencoder(1)
- LSTM(1)
- DLinear(1)
- ๊ฐ๋ (1)
- NIPS 2017(1)
- Anomaly Detection(1)
- yolov5(1)
- NLinear(1)
- Blood Glucose(1)
- KDD 2022(1)
- Attention(1)
- AAAI 2021(1)
- survey(1)
- ์์คํจ์(1)
- ์ฅ๊ธฐ ์๊ณ์ด(1)
- ์๊ณ์ด ์ด์์น ํ์ง(1)
- CVPR(1)
- KDD(1)
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] Masked Autoencoders Are Scalable Vision Learners(CVPR, 2021)
๐ ๋ณธ ๋ด์ฉ์ ๋ ผ๋ฌธ ์ ๋ฌธ์๊ฐ ๊ฐ์ธ์ ์ผ๋ก ํ๊ธฐํ ๋ด์ฉ์ ๋๋ค. ๋ด์ฉ์ ์ค๋ฅ๋ ํผ๋๋ฐฑ์ด ์์ผ๋ฉด ๋ง์ํด์ฃผ์๋ฉด ๊ฐ์ฌํ ๋ฐ์ํ๊ฒ ์ต๋๋ค.๐๐ ๊ฐ์ธ ๊ธฐ๋ก์ฉ ํฌ์คํธ์ ๋๋ค
[๋ฐฑ์ค] 11726๋ฒ 2xn ํ์ผ๋ง - ํ์ด์ฌ(Python)
โค๏ธ ์๊ณ ๋ฆฌ์ฆ - ๋ค์ด๋๋ฏน ํ๋ก๊ทธ๋๋ฐ - ๋ฐฑ์ค 11726 โค๏ธ
[๋ฐฑ์ค] 1463๋ฒ 1๋ก ๋ง๋ค๊ธฐ - ํ์ด์ฌ(Python)
โค๏ธ ์๊ณ ๋ฆฌ์ฆ - ๋ค์ด๋๋ฏน ํ๋ก๊ทธ๋๋ฐ - ๋ฐฑ์ค 1463 โค๏ธ
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] Attention Is All You Need (NIPS, 2017)
๐ Attention, Transformer์ ๋ํ ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] A PCB Dataset for Defects Detection and Classification
๐ pcb defect detection with SURF, ์ ์์ ์๊ณ๊ฐ ๋ถํ ์๊ณ ๋ฆฌ์ฆ, ์ค์๊ฐ ํํฐ๋ง ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] ONLINE PCB DEFECT DETECTOR ON A NEW PCB DEFECT DATASET (2019)
๐ pcb defect detection with GPP ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] PCB-Defect-Detection-using-Deepstream (2022)
๐ PCB defect detection with YOLOv5 ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] PCB Defect Detection Using Denoising Convolutional Autoencoders (2020)
๐ PCB defect detection with AutoEncoder ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[์๋ฒ ์ด ๋ฆฌ๋ทฐ] Visual Anomaly Detection for Images: A Survey
๐ image anomaly detection ๊ด๋ จ ์๋ฒ ์ด ๐
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] Are Transformers Effective for Time Series Forecasting? (AAAI, 2023) (NLinear, DLinear)
๐ NLinear, DLinear ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose (AAAI, 2023)
๐ AAAI 2023 ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] Outlier Impact Characterization for Time Series Data (AAAI,2021)
๐ AAAI 2021 ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[๋ ผ๋ฌธ ๋ฆฌ๋ทฐ] Greykite: Deploying Flexible Forecasting at Scale at LinkedIn (KDD,2022)
๐ KDD 2022 ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ ๐
[Deep Learning] Loss Function ์ด ์ ๋ฆฌ (MAE, MSE, RMSE, Cross Entropy)
๐ Loss Function (MAE, MSE, RMSE, Cross Entropy) ์ด ์ ๋ฆฌ ๐
[Michigan DL/cs231n] 13๊ฐ: Attention
๐ฅMichigan University Deep Learning 13๊ฐ๐ฅ
[Michigan DL/cs231n] 12๊ฐ: Recurrent Neural Networks
๐ฅMichigan University Deep Learning 12๊ฐ๐ฅ
[Michigan DL/cs231n] 11๊ฐ: Training Neural Networks (Part2)
๐ฅMichigan University Deep Learning 11๊ฐ๐ฅ
[Michigan DL/cs231n] 10๊ฐ: Training Neural Networks (Part1)
๐ฅMichigan University Deep Learning 10๊ฐ๐ฅ
[Michigan DL/cs231n] 8๊ฐ: CNN Architecture
๐ฅMichigan University Deep Learning 8๊ฐ๐ฅ
[Michigan DL/cs231n] 7๊ฐ: Convolutional Neural Network
๐ฅMichigan University Deep Learning 7๊ฐ๐ฅ