Footer

    Download on the App StoreGet it on Google Play

    關於

    • 認識 VoiceTube
    • 學習服務介紹
    • 加入我們
    • 常見問題
    • 熱門搜尋主題
    • 企業英文培訓
    • 社群推廣分潤計畫

    服務總覽

    • 口說挑戰
    • 單字單句本
    • Hero 智能學習
    • Tutor 真人家教
    • Vclass 名師課程
    • Campus 教育版
    • 字典查詢
    • 匯入影片並生成字幕
    • 部落格

    精選頻道

    影片分級

    • A1 初級
    • A2 初級
    • B1 中級
    • B2 中高級
    • C1 高級
    • C2 高級

    隱私權˙條款˙
    ©2026 VoiceTube Corporation. All rights reserved

    retrieval

    US /rɪˈtrivəl/

    ・

    UK /rɪˈtri:vl/

    B2 中高級英檢高級多益
    n. (u.)不可數名詞取回
    Data retrieval can be done easily with this program
    n. (u.)不可數名詞資料檢索
    Information retrieval is a key function of search engines.

    影片字幕

    黃仁勳暢談資料處理與生成式AI的未來! (黃仁勳談數據處理與生成式AI的未來)

    24:54黃仁勳暢談資料處理與生成式AI的未來! (黃仁勳談數據處理與生成式AI的未來)
    • You know that today's, and why it's such a big deal from a computer science perspective, today's computing experience is retrieval-based.

      要知道,從計算機科學的角度來看,當今的計算體驗是以檢索為基礎的,這也是為什麼它如此重要的原因。

    • The amount of internet traffic will be dramatically reduced, and it'll be much more generative with some retrieval to augment, right?

      互聯網流量將大幅減少,而且會通過一些檢索來增強生成性,對嗎?

    B1 中級

    Jerry Liu (LlamaIndex):打造真正自動化知識工作的 AI Agent! (Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex)

    17:57Jerry Liu (LlamaIndex):打造真正自動化知識工作的 AI Agent! (Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex)
    • RAG is just retrieval.

      RAG 只是檢索。

    • I know this is a RAG workshop, but RAG is just retrieval and then one-shot synthesis.

      我知道這是一個 RAG 工作坊,但 RAG 只是檢索,然後進行一次性合成。

    B2 中高級

    AI 代理人,一目瞭然! (AI Agents, Clearly Explained)

    10:09AI 代理人,一目瞭然! (AI Agents, Clearly Explained)
    • Pro tip, retrieval augmented generation, or RAG, is a fancy term that's thrown around a lot.

      專業提示:"檢索增強生成"(Retrieval augmented generation,簡稱 RAG)是一個常用的花哨術語。

    • Pro tip: Retrieval-Augmented Generation, or RAG, is a fancy term that's thrown around a lot.

      而這種試驗和錯誤迭代目前是由我這個人類完成的。

    B1 中級

    Amazon Web Services 教學 - DynamoDB 在 AWS 的使用教學! (Amazon Web Services Tutorial - Using DynamoDB with AWS)

    08:10Amazon Web Services 教學 - DynamoDB 在 AWS 的使用教學! (Amazon Web Services Tutorial - Using DynamoDB with AWS)
    • So that means every retrieval will be low latency, usually in the single digit millisecond.

      這意味著每次檢索的延遲時間都很短,通常只有個位數毫秒。

    • So that means every retrieval will be low latency, usually in the single-digit millisecond.

      這意味著每次檢索的延遲時間都很短,通常只有個位數毫秒。

    B1 中級

    中英雙語字幕 | 15分鐘掌握最新科技!黃仁勳揭示未來最大產業竟是「它」?GTC 2025 重磅發表! (中英大字幕 | 15分鐘掌握最新科技動態 | 黃仁勳揭露未來最大產業是它 | 2025 GTC 最重要的發表)

    15:27中英雙語字幕 | 15分鐘掌握最新科技!黃仁勳揭示未來最大產業竟是「它」?GTC 2025 重磅發表! (中英大字幕 | 15分鐘掌握最新科技動態 | 黃仁勳揭露未來最大產業是它 | 2025 GTC 最重要的發表)
    • From a retrieval computing model, we now have a generative computing model, whereas almost everything that we did in the past was about creating content in advance, storing multiple versions of it,

      生成式人工智能從根本上改變了計算方式。

    • From a retrieval computing model, we now have a generative computing model, whereas almost everything that we did in the past was about creating content in advance, storing multiple versions of it, and fetching whatever version we think is appropriate at the moment of use.

      從檢索計算模式來看,我們現在採用的是生成計算模式,而過去我們所做的幾乎所有事情都是提前創建內容、存儲多個版本,然後在使用時獲取我們認為合適的版本。

    B1 中級

    RAG vs 微調 vs 提示工程:AI 模型優化大比拼! (RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models)

    13:10RAG vs 微調 vs 提示工程:AI 模型優化大比拼! (RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models)
    • That is called RAG, or Retrieval Augmented Generation.

      這就是所謂的 RAG,即 "檢索增強生成"。

    • That is called RAG, or Retrieval-Augmented Generation.

      這是一種方法。

    B1 中級

    馬斯克與黃仁勳談論AI時笑翻!(完整重播) (Elon Musk Cracks Up In AI Talk With Jensen Huang (full replay))

    22:43馬斯克與黃仁勳談論AI時笑翻!(完整重播) (Elon Musk Cracks Up In AI Talk With Jensen Huang (full replay))
    • What is new about AI from a computer science perspective is that the way computing was done in the past was largely retrieval based computing.

      從電腦科學的角度來看,AI 的新之處在於過去的運算方式主要是基於檢索的運算。

    • It's a retrieval based computing model.

      這是一種基於檢索的運算模型。

    B1 中級

    記憶力:Crash Course 學習技巧 #3 (Memory: Crash Course Study Skills #3)

    10:52記憶力:Crash Course 學習技巧 #3 (Memory: Crash Course Study Skills #3)
    • And according to the forget-to-learn theory, which is presented in Benedict Carey's book How We Learn, memories actually have two different strengths: storage strength and retrieval strength.

      他開始對自己的記憶做無數的測試,逼自己去回想一長串無意義的字母,直到他想出了遺忘曲線

    • storage strength and retrieval strength.

      儲存力和檢索力

    B1 中級

    AI 技術堆疊是什麼?LLMs、RAG 與 AI 硬體解析! (What Is an AI Stack? LLMs, RAG, & AI Hardware)

    09:06AI 技術堆疊是什麼?LLMs、RAG 與 AI 硬體解析! (What Is an AI Stack? LLMs, RAG, & AI Hardware)
    • This could also include the pipelines to do any processing, pre processing, post processing of that data, as well as vector databases you may use or retrieval systems.

      這也可能包含處理、預處理、後處理這些資料的管線,以及你可能會使用的向量資料庫或檢索系統。

    • This could also include the pipelines to do any processing, pre-processing, post-processing of that data, as well as vector databases you may use or retrieval systems, also known as RAG.

      這很重要,因為基礎模型通常是根據公開資訊訓練的,而這些資訊不一定總是完整的。

    B1 中級

    2025年及以後的網路安全趨勢! (Cybersecurity Trends for 2025 and Beyond)

    16:552025年及以後的網路安全趨勢! (Cybersecurity Trends for 2025 and Beyond)
    • So, in other words, if we had a chatbot that didn't hallucinate, that was grounded in the facts, and we could do that with something like retrieval, augmented generation, rag technology, and things like that, it could do a better job of answering questions for cybersecurity analysts.

      是以,換句話說,如果我們有一個哈拉機器人,它不會產生幻覺,而是以事實為基礎,我們可以通過檢索、增強生成、抹布技術等方法做到這一點,它就能更好地回答網絡安全分析師的問題。

    • and we could do that with something like retrieval augmented generation, RAG technology, and

      因為生成式人工智能擅長的事情之一就是生成摘要。

    A2 初級