๋ชฉ๋ก๐ฉ๐ป ์ธ๊ณต์ง๋ฅ (ML & DL) (100)
๐ ๊ณต๋ถํ๋ ์ง์ง์ํ์นด๋ ์ฒ์์ด์ง?
![](http://i1.daumcdn.net/thumb/C150x150/?fname=https://blog.kakaocdn.net/dn/MO8VJ/btrMgRCYW7j/cn8202ANI6soGrgJRhkXjk/img.png)
220916 ์์ฑ https://www.kaggle.com/code/koheimuramatsu/change-detection-forecasting-in-smart-home/notebook Change Detection & Forecasting in Smart Home Explore and run machine learning code with Kaggle Notebooks | Using data from Smart Home Dataset with weather Information www.kaggle.com ๐ energy data from house appliances and weather information ๊ฐ์ ์ ํ๋ณ ์๋์ง ์๋น๋๊ณผ ๊ธฐ๊ฐ ๊ฐ์ ๊ด๊ณ๋ฅผ ์ดํด ๊ฐ์ ์ ํ์ ์ด์ ์ฌ์ฉ์ ๊ฐ์ง ๋ ์จ ์ ๋ณด์ ..
![](http://i1.daumcdn.net/thumb/C150x150/?fname=https://blog.kakaocdn.net/dn/oJ05I/btrMfej6vHo/3RT0IPRGTH26mZZa2shokK/img.png)
220916 ์์ฑ https://www.kaggle.com/code/ymlai87416/web-traffic-time-series-forecast-with-4-model Web traffic time series forecast with 4 model Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources www.kaggle.com ๐ ์น ํธ๋ํฝ ์๊ณ์ด ์์ธก ์ฝ 145,000๊ฐ์ Wikipedia ๊ธฐ์ฌ์ ๋ํ ๋ฏธ๋ ์น ํธ๋ํฝ ์์ธก ๋ฌธ์ ์ ๋ํด ์ฐธ๊ฐ์๊ฐ ์ค๊ณํ ์ต์ฒจ๋จ ๋ฐฉ๋ฒ์ ํ ์คํธ ๐ ๋ฐ์ดํฐ ์ธํธ ์ฝ 145,000๊ฐ์ ์๊ณ์ด๋ก ๊ตฌ์ฑ 2015๋ 7์ 1์ผ๋ถํฐ 2016๋ 12์ 31์ผ๊น์ง..
![](http://i1.daumcdn.net/thumb/C150x150/?fname=https://blog.kakaocdn.net/dn/d3vrGw/btrMcTm3qR6/WbKy6CGaaQd77Galx1fRb0/img.png)
220915 ์์ฑ https://arxiv.org/abs/2011.04452 Comparison between ARIMA and Deep Learning Models for Temperature Forecasting Weather forecasting benefits us in various ways from farmers in cultivation and harvesting their crops to airlines to schedule their flights. Weather forecasting is a challenging task due to the chaotic nature of the atmosphere. Therefore lot of research a arxiv.org ๐ฃ Abstract..
![](http://i1.daumcdn.net/thumb/C150x150/?fname=https://blog.kakaocdn.net/dn/bqZ9kG/btrMbwY12Vk/rn25YsamFLMmwe0uXvYhX1/img.png)
220915 ์์ฑ https://dhi.github.io/tsod/ tsod: Anomaly Detection for time series data. — tsod documentation dhi.github.io https://github.com/DHI/tsod GitHub - DHI/tsod: Anomaly Detection for time series data Anomaly Detection for time series data. Contribute to DHI/tsod development by creating an account on GitHub. github.com ๐ tsod ๋? ์ด์ ํ์์ ๊ฒฝ๊ณ ์กฐ๊ฑด ๋๋ ์ค์๊ฐ ๊ฒฐ์ ์์คํ ์ผ๋ก ์์น ์๋ฎฌ๋ ์ด์ ์์ง์ ๋ฐ์ดํฐ๋ฅผ ์ ๊ณตํ๊ธฐ ์ ์ ์๋์ผ๋ก ๊ฐ์ง๋..
![](http://i1.daumcdn.net/thumb/C150x150/?fname=https://blog.kakaocdn.net/dn/sRZLD/btrL3ExgQSH/KEb1Wf5DxV79FCIJlepkbK/img.png)
220914 ์์ฑ https://github.com/haenara-shin/DACON/blob/main/2_TimeSeries_%ED%83%9C%EC%96%91%EA%B4%91%EB%B0%9C%EC%A0%84%EB%9F%89%EC%98%88%EC%B8%A1_KAERI/%5BPrediction_of_PV_Power_Generation%5D_Stacking_Quantile_Regression_Final_submission.ipynb GitHub - haenara-shin/DACON: DACON competition code repos. DACON competition code repos. Contribute to haenara-shin/DACON development by creating an account..
220914 ์์ฑ https://blog.naver.com/handuelly/221822938182 Keras - ๋ค์ธต Sequential Model(), compile(), fit() # Sequention Model(๋ค์ธต) # 5๋ฒ ๋ผ์ธ, dense_1 : ์ ๊ฒฝ๋ง ํ๋๋น 3๊ฐ์ ํ๋ผ๋ฏธํฐ(2๊ฐ์ Input + 1๊ฐ์ ... blog.naver.com https://wikidocs.net/32105 07) ์ผ๋ผ์ค(Keras) ํ์ด๋ณด๊ธฐ ์ด ์ฑ ์์๋ ๋ฅ ๋ฌ๋์ ์ฝ๊ฒ ํ ์ ์๋ ํ์ด์ฌ ๋ผ์ด๋ธ๋ฌ๋ฆฌ์ธ ์ผ๋ผ์ค(Keras)๋ฅผ ์ฌ์ฉํฉ๋๋ค. ์ผ๋ผ์ค๋ ์ ์ ๊ฐ ์์ฝ๊ฒ ๋ฅ ๋ฌ๋์ ๊ตฌํํ ์ ์๋๋ก ๋์์ฃผ๋ ์์ ๋ ๋ฒจ์ ์ธํฐ ... wikidocs.net ๐ complie() : ๋ชจ๋ธ์ ๋น๋ํ๊ณ ์คํํ๊ธฐ ์ ์ ์ปดํ์ผ ํ๋ ํ..
![](http://i1.daumcdn.net/thumb/C150x150/?fname=https://blog.kakaocdn.net/dn/2DNRu/btrL8Zgju3G/ncAaH0CI9Rm1WzP8w35VDk/img.webp)
220914 ์์ฑ ๐ Batch Normalization Batch ๋จ์๋ก ํ ๋ ์ด์ด์ ์ ๋ ฅ์ผ๋ก ๋ค์ด์ค๋ ๋ชจ๋ ๊ฐ๋ค์ ์ด์ฉํด์ ํ๊ท ๊ณผ ๋ถ์ฐ์ ๊ตฌํจ feature element๋ณ๋ก(์ฐจ์๋ณ๋ก) ํ๊ท ๊ณผ ๋ถ์ฐ์ ๊ตฌํจ ๋ฐ๋๋ก, Conv Layer์ Activation map(์ฑ๋, Depth)๋ง๋ค ํ๊ท ๊ณผ ๋ถ์ฐ์ ํ๋๋ง ๊ตฌํจ -> ๋ฐ์ดํฐ์ '๊ณต๊ฐ์ ๊ตฌ์กฐ(Spatial Structure)'๊ฐ ์ ์ ์ง๋๊ธฐ๋ฅผ ๋ฐ๋ -> So, CNN Activation Map์ normalize ํ ๋๋ ์ ์ฒด map์ ํ๊ท ๊ณผ ๋ถ์ฐ์ ๊ฐ์ด ๊ตฌํจ ํ๊ท ๊ณผ ๋ถ์ฐ๊ฐ์ ์ด์ฉํด Normalization Batch Norm์ ๋ฏธ๋ถ์ด ๊ฐ๋ฅ ์์ Convolution - Batch Normalization - Activation - Dropout - P..
![](http://i1.daumcdn.net/thumb/C150x150/?fname=https://blog.kakaocdn.net/dn/lgcpB/btrLGkdWt9N/dmAutx7zn8Hkp3N8ilytfk/img.gif)
220908 ์์ฑ https://www.ibm.com/docs/ko/spss-statistics/25.0.0?topic=modeler-custom-arima-models ์ฌ์ฉ์ ์ ์ ARIMA ๋ชจํ ์๊ณ์ด ๋ชจ๋ธ๋ฌ๋ฅผ ์ฌ์ฉํ์ฌ ๊ณ ์ ์์ธก๋ณ์ ์ธํธ๊ฐ ํฌํจ๋๊ฑฐ๋ ํฌํจ๋์ง ์์ Box-Jenkins1 ๋ชจํ์ด๋ผ๊ณ ๋ ํ๋ ์ฌ์ฉ์ ์ ์ ๋น๊ณ์ ๋๋ ๊ณ์ ARIMA(์๊ธฐํ๊ท ์ง์ ์ด๋ ํ๊ท ) ๋ชจํ์ ์ค์ ํฉ๋๋ค. ์์ www.ibm.com https://otexts.com/fppkr/arima.html Chapter 8 ARIMA ๋ชจ๋ธ | Forecasting: Principles and Practice 2nd edition otexts.com https://byeongkijeong.github.io/ARIMA-with-..