https://note.rua.dev/Recent content on Jin'sHugo -- gohugo.ioen-usMon, 29 Jan 2024 15:16:46 +0800https://note.rua.dev/posts/building-a-latex-environment-with-basictex-on-macos/Mon, 29 Jan 2024 15:16:46 +0800https://note.rua.dev/posts/building-a-latex-environment-with-basictex-on-macos/LaTeX is a popular typesetting system, especially useful in academia. For macOS users, BasicTeX offers a lightweight alternative to the full MacTeX distribution. What is BasicTeX? BasicTeX is a minimal version of MacTeX. It’s only 80 MB compared to several GBs of MacTeX, including just the core TeX command-line tools. Install BasicTeX Use Homebrew to install BasicTeX: brew install --cask basictex Install local::lib The local::lib is a Perl module that creates a locally installed perl module library.https://note.rua.dev/posts/sageformer-series-aware-graph-enhanced-transformers-for-multivariate-time-series-forecasting/Wed, 11 Oct 2023 15:54:49 +0800https://note.rua.dev/posts/sageformer-series-aware-graph-enhanced-transformers-for-multivariate-time-series-forecasting/Zhang, Zhenwei Wang, Xin Gu, Yuantao SageFormer is a specialized model adept at multivariate time series forecasting. It effectively models dependencies between different series using graph structures. Key features of SageFormer include: Series-Aware and Graph-Enhanced Architecture: Enhances Transformer models to address temporal patterns and redundancy. Multivariate Time Series Forecasting: Efficiently forecasts multivariate time series, tackling challenges like representing diverse temporal patterns across series and reducing redundant information. Introduction SageFormer aims to resolve several challenges:https://note.rua.dev/friends/Tue, 10 Oct 2023 20:51:16 +0800https://note.rua.dev/friends/ StarryFK 个人博客https://note.rua.dev/posts/class-balanced-loss-based-on-effective-number-of-samples/Tue, 10 Oct 2023 17:55:33 +0800https://note.rua.dev/posts/class-balanced-loss-based-on-effective-number-of-samples/Yin Cui Menglin Jia Tsung-Yi Lin Yang Song Serge Belongie CB Loss (Class-Balanced Loss) is a method developed for calculating loss, targeting the challenges brought by long-tailed data distribution: Aim: Address the issue of long-tailed data distribution. Particularly beneficial in scenarios like image recognition and other machine learning tasks where the sample count for some classes significantly surpasses others. Characteristics: Introduction of a new weighting scheme: Utilizes the effective number of samples for each class.https://note.rua.dev/posts/focal-loss-for-dense-object-detection/Mon, 07 Aug 2023 16:05:20 +0800https://note.rua.dev/posts/focal-loss-for-dense-object-detection/Tsung-Yi Lin Priya Goyal Ross Girshick Kaiming He Piotr Dollár Focal Loss is a loss calculation method. Its characteristics are: Control the weight of the positive and negative samples. Control the weight of samples that are easy to classify and difficult to classify. Cross entropy $$ CE(p, y) = \left\{\begin{matrix} -log(p) & \text{if} \ y = 1 \\ -log(1-p) & \text{otherwise} \end{matrix}\right. $$ Where, $p$ is the predicted value, $y$ is the actual value.