Shared Memory
Ubuntu PPPoE 連線設定
Ubuntu 與 Windows 檔案傳輸方法
常見降維方法 - PCA、tSNE、UMAP
Feature Decoupling
Introduction
Feature decoupling is a technique used in machine learning and feature engineering to improve the performance and interpretability of models by separating correlated or redundant features into independent components. The main goal of feature decoupling is to simplify the representation of data while retaining the most relevant information for the task at hand.
Dual Learning
Introduction
Dual learning is a paradigm in machine learning that leverages the duality between two related tasks to improve learning efficiency and performance. The basic idea of dual learning is to train two models simultaneously, each focusing on a different aspect of the problem, while using feedback from one model to improve the learning of the other.
Contrastive Learning
Introduction
Contrastive learning is a machine learning technique used for representation learning, where the goal is to learn useful representations of data points by contrasting them with each other. The basic idea is to encourage similar data points to be closer to each other in the learned representation space while pushing dissimilar data points further apart.
Explainable Artificial Intelligence
Introduction
Explainable Artificial Intelligence (XAI) refers to the set of techniques and methodologies aimed at making the outputs and decisions of AI systems understandable to humans. The goal of XAI is to increase transparency, trust, and accountability in AI systems by providing insights into how they arrive at their conclusions.