Long Lin
Member since 2025
Diamond League
16710 points
Member since 2025
With this course you will learn how to use different techniques to fine-tune Gemini. Model tuning is an effective way to customize large models like Gemini for your specific tasks. It's a key step to improve the model's quality and efficiency. This course will give an overview of model tuning, describe the tuning options available for Gemini, help you determine when each tuning option should be used and how to perform tuning.
This course is part 1 of a 3-course series on Serverless Data Processing with Dataflow. In this first course, we start with a refresher of what Apache Beam is and its relationship with Dataflow. Next, we talk about the Apache Beam vision and the benefits of the Beam Portability framework. The Beam Portability framework achieves the vision that a developer can use their favorite programming language with their preferred execution backend. We then show you how Dataflow allows you to separate compute and storage while saving money, and how identity, access, and management tools interact with your Dataflow pipelines. Lastly, we look at how to implement the right security model for your use case on Dataflow.
本課程將介紹注意力機制,說明這項強大技術如何讓類神經網路專注於輸入序列的特定部分。此外,也將解釋注意力的運作方式,以及如何使用注意力來提高各種機器學習任務的成效,包括機器翻譯、文字摘要和回答問題。
In this course, we introduce you to Google Chat, Google’s chat software included with Google Workspace. You will learn about messaging individuals and groups in Google Chat. You will also discover customization options, collaboration features and how Google Chat integrates with other Google Workspace products. We will explore the use of spaces in Google Chat, showing you how to create, manage, search, and join them. Additionally, you will understand the distinctions between using a space and a group chat. You also explore Google Chat apps and learn how to search for and use apps within Google Chat. Aside from course videos, you will complete hands-on activities to practice what you’ve learned. Consider inviting a colleague or two to interact with you in Google Chat as you complete the activities.
This course shows learners the benefits of using Google Cloud to stream and broadcast content. The course provides a high-level overview of the infrastructure required for streaming and broadcasting.
本課程概要說明解碼器與編碼器的架構,這種強大且常見的機器學習架構適用於序列對序列的任務,例如機器翻譯、文字摘要和回答問題。您將認識編碼器與解碼器架構的主要元件,並瞭解如何訓練及提供這些模型。在對應的研究室逐步操作說明中,您將學習如何從頭開始使用 TensorFlow 寫程式,導入簡單的編碼器與解碼器架構來產生詩詞。
這個入門微學習課程主要介紹「負責任的 AI 技術」和其重要性,以及 Google 如何在自家產品中導入這項技術。本課程也會說明 Google 的 7 個 AI 開發原則。
A short course on defining and managing teams and organizations in Google AppSheet.
本課程說明如何使用深度學習來建立圖像說明生成模型。您將學習圖像說明生成模型的各個不同組成部分,例如編碼器和解碼器,以及如何訓練和評估模型。在本課程結束時,您將能建立自己的圖像說明生成模型,並使用模型產生圖像說明文字。
這堂課程將說明變換器架構,以及基於變換器的雙向編碼器表示技術 (BERT) 模型,同時帶您瞭解變換器架構的主要組成 (如自我注意力機制) 和如何用架構建立 BERT 模型。此外,也會介紹 BERT 適用的各種任務,像是文字分類、問題回答和自然語言推論。課程預計約 45 分鐘。
Migration from MySQL to Cloud Spanner using Dataflow that includes sample mock data and all necessary steps with initial assessment to validation including taking care of migrating users and grants.
這是一堂入門級的微學習課程,旨在探討大型語言模型 (LLM) 的定義和用途,並說明如何調整提示來提高 LLM 成效。此外,也會介紹多項 Google 工具,協助您自行開發生成式 AI 應用程式。
這堂初級課程將介紹 Google Cloud 的資料分析工作流程,以及用於探索、分析資料並以圖表呈現的工具。您也能學會如何與相關人員分享自己的發現結果。本課程包含個案研究、實作實驗室、講座、測驗和示範,實際展示如何將原始資料集轉化為清晰的資料,進而呈現出能發揮成效的圖表和資訊主頁。無論您是資料領域從業人員、想瞭解如何透過 Google Cloud 取得成功,或有意在職涯中更上一層樓,本課程都能協助您踏出第一步。絕大多數在工作上執行或運用資料分析的學員,都能從本課程受益。
Discover flows in Conversational Agents and learn how to build deterministic chat and voice experiences with language models. Explore key concepts like drivers, intents, and entities, and how to use them to create conversational agents.
This course will teach you how to build conversational experiences for Conversational Agents using Generative Playbooks. You'll start with an introduction to playbooks and learn how to set up your first one. You'll also learn about the importance of testing, as well as key production considerations like quota limits and integration. The course concludes with a case study that shows how to use playbooks for generative steering.
Unlock the power of generative AI to create intelligent, automated agents. After completing this course, you'll be equipped to develop a data store agent that can instantly answer complex questions by automatically extracting and synthesizing information from your websites, documents, or structured data. Say goodbye to static FAQs—your new agent will provide dynamic, accurate answers and even surface the original source URLs, all with a simple and rapid setup.
This course explores the foundational principles of conversation design to craft engaging and effective chatbot experiences that emulate human-like experiences.
In this course, you'll dive deep into the essential topics you need to know to design, build, and maintain a powerful CES solution. Get ready to transform your understanding of what's possible and create an architecture that drives customer satisfaction. This course is designed to introduce you to the architecture of the Customer Engagement Suite (CES). You'll explore the main considerations for building and implementing Conversational AI solutions including key architectural components and integrations. You'll also explore how Conversational AI interacts with Vertex AI and get a high-level overview of the key features of the Conversational AI Platform.
In this course you will learn how to leverage Conversational Insights to uncover hidden information from your contact center data to increase operational efficiency and drive data-driven business decisions.
Transform your understanding of customer service with this course on the Customer Engagement Suite (CES) and its powerful generative AI capabilities. You'll start by tracing the journey of contact centers, understanding how they've evolved and where gen AI is propelling them next. Then, you'll gain a deep understanding of the core building blocks within the CES solution, seeing how each component contributes to delivering exceptional customer experiences. The course concludes by exploring the robust business case for CES, along with practical use cases and the various user personas that benefit from this innovative solution.
完成「實現雲端協作與生產力工作流」課程,即可獲得入門級技能徽章。本課程將介紹 Google 的協作平台, 帶您瞭解如何使用 Gmail、日曆、Meet、雲端硬碟、試算表和 AppSheet。
歡迎來到 Cloud TPU 課程。我們將探討在各種情境下使用 TPU 的優缺點,並比較不同的 TPU 加速器,協助您選擇合適的工具。您將瞭解如何盡可能提高 AI 模型的效能和效率,以及互通的 GPU/TPU 對於打造靈活的機器學習工作流程有多重要。我們會透過引人入勝的內容和實際演示,一步步引導您有效運用 TPU。
想瞭解 AI 背後的強大硬體嗎?本單元將深入解析針對效能最佳化的 AI 電腦,說明其重要性。我們將探討 CPU、GPU 和 TPU 如何大幅加速 AI 任務運算,分析各自的特點,以及 AI 軟體如何充分利用這些硬體效能。單元結束後,您將清楚掌握如何根據 AI 專案挑選合適的 GPU,並做出明智的 AI 工作負載決策。
準備開始使用 AI Hypercomputer 了嗎?這門課程可讓您快速上手!我們將介紹這個架構的基本概念,以及此架構如何幫助 AI 處理 AI 工作負載。您將瞭解 Hypercomputer 內的不同元件,例如 GPU、TPU 和 CPU,以及如何視需求選擇合適的部署方法。
在本課程中,您會學到 Google Cloud 上的資料工程、資料工程師的角色與職責,以及這些內容如何對應至 Google Cloud 提供的服務。您也將瞭解處理資料工程難題的許多方法。
在 「Google Kubernetes Engine 架構:基礎知識」的課程中,您將復習 Google Cloud 的配置和原則,接著是建立和管理軟體容器簡介和 Kubernetes 架構簡介。 這是 Google Kubernetes Engine 架構系列中的第一項課程。完成此課程後,請註冊 Google Kubernetes Engine 架構:工作負載課程。
本課程針對評估生成式和預測式 AI 模型,向機器學習從業人員介紹相關的基礎工具、技術和最佳做法。模型評估是機器學習的重要領域,確保這類系統能在正式環境中提供可靠、準確且成效優異的結果。 學員將深入瞭解多種評估指標與方法,以及適用於不同模型類型和工作的應用方式。此外,也會特別介紹生成式 AI 模型帶來的獨特難題,並提供有效的應對策略。透過 Google Cloud Vertex AI 平台,學員將瞭解在模型挑選、最佳化和持續監控方面,該如何導入穩健的評估程序。
本課程旨在提供必要的知識和工具,協助您探索機器學習運作團隊在部署及管理生成式 AI 模型時面臨的獨特挑戰,並瞭解 Vertex AI 如何幫 AI 團隊簡化機器學習運作程序,打造成效非凡的生成式 AI 專案。
完成「在 Google Cloud 使用機器學習 API」課程,即可獲得進階技能徽章。本課程說明以下機器學習和 AI 技術的基本功能: Cloud Vision API、Cloud Translation API 和 Cloud Natural Language API。
This course helps learners create a study plan for the PDE (Professional Data Engineer) certification exam. Learners explore the breadth and scope of the domains covered in the exam. Learners assess their exam readiness and create their individual study plan.