從這裡開始
從這裡開始
五 基於結果的課程
每門課程都包括明確的成果、映射的能力、實踐活動和應用的頂點。
主題曲目
按曲目瀏覽
跳入您關心的領域。每條賽道都有多個簡單的英文指南。
- 91 指南基礎知識核心概念：人工智慧如何在高層次上運作。探索
- 177 指南語言人工智慧LLM、NLP、ChatGPT、提示和文字理解。探索
- 170 指南視覺人工智慧影像生成、電腦視覺、視訊和設計。探索
- 124 指南音訊人工智慧語音、音樂、播客和音訊優先的人工智慧。探索
- 123 指南公司OpenAI、Anthropic、Google、Meta 等的設定檔。探索
- 346 指南應用領域人工智慧如何出現在編碼、搜尋、代理和日常生活中。探索
- 165 指南產業醫療保健、金融、教育、能源等領域的人工智慧。探索
- 319 指南科技晶片、微調、RAG、向量和人工智慧基礎設施。探索
- 142 指南社會偏見、隱私、版權、安全和人工智慧的未來。探索
全庫
所有指南
1657 的 1657 顯示指南。按曲目過濾或上方搜尋。
- 科技套索和彈性網絡回歸Lasso regression adds an L1 penalty that can shrink some fitted coefficients exactly to zero, producing a sparse linear model.4 最小閱讀量閱讀
- 科技線性迴歸假設與殘差分析Linear regression describes a conditional mean as a linear combination of predictors, but reliable interpretation and uncertainty estimates depend…4 最小閱讀量閱讀
- 科技Log and Box-Cox TransformationsLog, Box-Cox, and Yeo-Johnson transformations reshape numeric distributions, often reducing right skew and stabilizing variation before modeling.3 最小閱讀量閱讀
- 科技MAP 估計和先驗Maximum a posteriori (MAP) estimation chooses the parameter value with the highest posterior density for a continuous parameter, or posterior mass…3 最小閱讀量閱讀
- 科技Multicollinearity and Variance Inflation FactorMulticollinearity occurs when predictors in a regression carry overlapping information, making it difficult to separate their individual contributions.4 最小閱讀量閱讀
- 科技序數回歸Ordinal regression predicts ordered categories such as low, medium and high while using their order without assuming equal numeric gaps.3 最小閱讀量閱讀
- 科技計數數據的泊松回歸Poisson regression models the expected value of a count as a function of predictors, commonly using a log link to keep fitted means positive.4 最小閱讀量閱讀
- 科技Softmax Regression for Multiclass ClassificationSoftmax regression extends logistic regression to mutually exclusive classes by assigning each class a score and converting all scores into probabilities…3 最小閱讀量閱讀
- 科技XGBoost AlgorithmXGBoost is a gradient-boosting library that builds an additive predictor by fitting new trees to improve the current objective, with regularization…3 最小閱讀量閱讀
- 科技Expectation-Maximization AlgorithmExpectation-maximization (EM) estimates model parameters when data include unobserved variables or missing values by alternating between estimating…3 最小閱讀量閱讀
- 科技基尼雜質Gini impurity measures how mixed the class labels are in a decision-tree node, with zero indicating that every example belongs to one class.4 最小閱讀量閱讀
- 科技KL DivergenceKullback-Leibler (KL) divergence measures the expected extra information cost of using one probability distribution to represent another.3 最小閱讀量閱讀