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。
- 134 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
- 272 指南語言人工智慧LLM、NLP、ChatGPT、提示和文字理解。探索
- 298 指南視覺人工智慧影像生成、電腦視覺、視訊和設計。探索
- 188 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
- 145 指南公司OpenAI、Anthropic、Google、Meta 等的設定檔。探索
- 761 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
- 244 指南產業醫療保健、金融、教育、能源等領域的人工智慧。探索
- 536 指南科技晶片、微調、RAG、向量和人工智慧基礎設施。探索
- 422 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
3000 的 3000 顯示指南。按曲目過濾或上方搜尋。
- 科技知識蒸餾Knowledge distillation trains a student model using a teacher model’s outputs or representations as supervision. Free plain-English guide.2 最小閱讀量閱讀
- 科技專家薈萃Sparse Mixture of Experts layers use a router to select a subset of expert networks for each token. Free plain-English guide.2 最小閱讀量閱讀
- 基礎知識嵌入Embeddings represent items with numerical vectors whose relationships depend on the representation and training objective. Free plain-English guide.3 最小閱讀量閱讀
- 基礎知識代幣化Tokenization converts text into units and numerical identifiers used by a language model. Free plain-English guide.3 最小閱讀量閱讀
- 基礎知識特徵工程Feature engineering transforms raw measurements into inputs for a model. Free plain-English guide.3 最小閱讀量閱讀
- 科技模型量化Model quantization represents selected neural-network values with lower-precision formats to reduce their storage or computation costs.2 最小閱讀量閱讀
- 科技聯邦學習Federated learning trains a shared model through participants’ local computations and aggregated updates while leaving their training records decentralized.2 最小閱讀量閱讀
- 基礎知識決策樹與隨機森林A decision tree routes inputs through feature-based splits to a prediction at a leaf. Free plain-English guide.3 最小閱讀量閱讀
- 基礎知識支援向量機Support vector machines are supervised methods whose classification formulations balance a separating margin with fitting the training labels.3 最小閱讀量閱讀
- 基礎知識降維Dimensionality reduction represents data with fewer coordinates for tasks such as compression, visualization, or downstream modeling.3 最小閱讀量閱讀
- 基礎知識遷移學習Transfer learning reuses a previously trained model or its representations for another task. Free plain-English guide.3 最小閱讀量閱讀
- 基礎知識自我監督學習Self-supervised learning obtains a training signal from the data or transformations of it rather than requiring a task label for every example.3 最小閱讀量閱讀