Gobinath Velusamy
Member since 2022
Silver League
19310 points
Member since 2022
This course explores the benefits of using Vertex AI Feature Store, how to improve the accuracy of ML models, and how to find which data columns make the most useful features. This course also includes content and labs on feature engineering using BigQuery ML, Keras, and TensorFlow.
The course begins with a discussion about data: how to improve data quality and perform exploratory data analysis. We describe Vertex AI AutoML and how to build, train, and deploy an ML model without writing a single line of code. You will understand the benefits of Big Query ML. We then discuss how to optimize a machine learning (ML) model and how generalization and sampling can help assess the quality of ML models for custom training.
本課程介紹 Google Cloud 的 AI 和機器學習 (ML) 功能,著重說明如何開發生成式和預測式 AI 專案。我們也會探討「從資料到 AI」整個生命週期都適用的技術、產品和工具,並透過互動式練習,協助資料科學家、AI 開發人員和機器學習工程師精進專業知識。
完成「在 Compute Engine 導入 Cloud Load Balancing」技能徽章入門課程,即可證明您具備下列技能: 在 Compute Engine 建立及部署虛擬機器, 以及設定網路和應用程式負載平衡器。
In this second installment of the Dataflow course series, we are going to be diving deeper on developing pipelines using the Beam SDK. We start with a review of Apache Beam concepts. Next, we discuss processing streaming data using windows, watermarks and triggers. We then cover options for sources and sinks in your pipelines, schemas to express your structured data, and how to do stateful transformations using State and Timer APIs. We move onto reviewing best practices that help maximize your pipeline performance. Towards the end of the course, we introduce SQL and Dataframes to represent your business logic in Beam and how to iteratively develop pipelines using Beam notebooks.
In the last installment of the Dataflow course series, we will introduce the components of the Dataflow operational model. We will examine tools and techniques for troubleshooting and optimizing pipeline performance. We will then review testing, deployment, and reliability best practices for Dataflow pipelines. We will conclude with a review of Templates, which makes it easy to scale Dataflow pipelines to organizations with hundreds of users. These lessons will help ensure that your data platform is stable and resilient to unanticipated circumstances.
完成使用 BigQuery ML 為預測模型進行資料工程技能徽章中階課程, 即可證明自己具備下列知識與技能:運用 Dataprep by Trifacta 建構連至 BigQuery 的資料轉換 pipeline; 使用 Cloud Storage、Dataflow 和 BigQuery 建構「擷取、轉換及載入」(ETL) 工作負載, 以及使用 BigQuery ML 建構機器學習模型。
完成 在 Google Cloud 為機器學習 API 準備資料 技能徽章入門課程,即可證明您具備下列技能: 使用 Dataprep by Trifacta 清理資料、在 Dataflow 執行資料管道、在 Managed Service for Apache Spark 建立叢集和執行 Apache Spark 工作,以及呼叫機器學習 API,包含 Cloud Natural Language API、Google Cloud Speech-to-Text API 和 Video Intelligence API。
完成 透過 BigQuery 建構資料倉儲 技能徽章中階課程,即可證明您具備下列技能: 彙整資料以建立新資料表、排解彙整作業問題、利用聯集附加資料、建立依日期分區的資料表, 以及在 BigQuery 使用 JSON、陣列和結構體。
In this intermediate course, you will learn to design, build, and optimize robust batch data pipelines on Google Cloud. Moving beyond fundamental data handling, you will explore large-scale data transformations and efficient workflow orchestration, essential for timely business intelligence and critical reporting. Get hands-on practice using Dataflow for Apache Beam and Serverless for Apache Spark (Dataproc Serverless) for implementation, and tackle crucial considerations for data quality, monitoring, and alerting to ensure pipeline reliability and operational excellence. A basic knowledge of data warehousing, ETL/ELT, SQL, Python, and Google Cloud concepts is recommended.
Text Prompt Engineering Techniques introduces you to consider different strategic approaches & techniques to deploy when writing prompts for text-based generative AI tasks.
This content is deprecated. Please see the latest version of the course, here.
This course will help ML Engineers, Developers, and Data Scientists implement Large Language Models for Generative AI use cases with Vertex AI. The first two modules of this course contain links to videos and prerequisite course materials that will build your knowledge foundation in Generative AI. Please do not skip these modules. The advanced modules in this course assume you have completed these earlier modules.
(Previously named "Developing apps with Vertex AI Agent Builder: Search". Please note there maybe instances in this course where previous product names and titles are used) Enterprises of all sizes have trouble making their information readily accessible to employees and customers alike. Internal documentation is frequently scattered across wikis, file shares, and databases. Similarly, consumer-facing sites often offer a vast selection of products, services, and information, but customers are frustrated by ineffective site search and navigation capabilities. This course teaches you to use AI Applications to integrate enterprise-grade generative AI search.
隨著企業持續擴大使用人工智慧和機器學習,以負責任的方式發展相關技術也日益重要。對許多企業來說,談論負責任的 AI 技術可能不難,如何付諸實行才是真正的挑戰。如要瞭解如何在機構中導入負責任的 AI 技術,本課程絕對能助您一臂之力。 您可以從中瞭解 Google Cloud 目前採取的策略、最佳做法和經驗談,協助貴機構奠定良好基礎,實踐負責任的 AI 技術。
本課程會介紹 Vertex AI Studio。您可以運用這項工具和生成式 AI 模型互動、根據商業構想設計原型,並投入到正式環境。透過身歷其境的應用實例、有趣的課程及實作實驗室,您將能探索從提示到正式環境的生命週期,同時學習如何將 Vertex AI Studio 運用在多模態版 Gemini 應用程式、提示設計、提示工程和模型調整。這個課程的目標是讓您能運用 Vertex AI Studio,在專案中發揮生成式 AI 的潛能。
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。
Learn how to use Gemini Notebook to create a personalized study guide for the Professional Data Engineer certification exam. You'll review Gemini Notebook features, create a notebook in Gemini Notebook, and learn how to use a study guide to practice for a certification exam.
While the traditional approaches of using data lakes and data warehouses can be effective, they have shortcomings, particularly in large enterprise environments. This course introduces the concept of a data lakehouse and the Google Cloud products used to create one. A lakehouse architecture uses open-standard data sources and combines the best features of data lakes and data warehouses, which addresses many of their shortcomings.
This course introduces the Google Cloud big data and machine learning products and services that support the data-to-AI lifecycle. It explores the processes, challenges, and benefits of building a big data pipeline and machine learning models with Vertex AI on Google Cloud.
Incorporating machine learning into data pipelines increases the ability to extract insights from data. This course covers ways machine learning can be included in data pipelines on Google Cloud. For little to no customization, this course covers AutoML. For more tailored machine learning capabilities, this course introduces Notebooks and BigQuery machine learning (BigQuery ML). Also, this course covers how to productionalize machine learning solutions by using Vertex AI.
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。
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。
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。
本課程將介紹擴散模型,這是一種機器學習模型,近期在圖像生成領域展現亮眼潛力。概念源自物理學,尤其深受熱力學影響。過去幾年來,在學術界和業界都是炙手可熱的焦點。在 Google Cloud 中,擴散模型是許多先進圖像生成模型和工具的基礎。課程將介紹擴散模型背後的理論,並說明如何在 Vertex AI 上訓練和部署這些模型。
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。
Earn a skill badge by passing the final quiz, you'll demonstrate your understanding of foundational concepts in generative AI. A skill badge is a digital badge issued by Google Cloud in recognition of your knowledge of Google Cloud products and services. Share your skill badge by making your profile public and adding it to your social media profile.
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。
這個入門微學習課程主要說明生成式 AI 的定義和使用方式,以及此 AI 與傳統機器學習方法的差異。本課程也會介紹各項 Google 工具,協助您開發自己的生成式 AI 應用程式。
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.
各種規模的機構都開始運用雲端的強大功能和靈活性,徹底改變營運方式。不過,有效管理及擴充雲端資源可能是相當複雜的工作。本課程將探討在雲端中的現代營運、可靠性和韌性的基礎概念,以及 Google Cloud 如何協助您達成這些目標。本課程是 Cloud Digital Leader 學習路徑的一部分,旨在促進個人職能發展,並打造企業的未來。
許多傳統企業使用舊版系統和應用程式,無法滿足現今客戶的期望。企業主管經常需要在維護老舊的 IT 系統,以及投資新產品/服務之間做出選擇。本課程將探討這些挑戰,並提供解決方案,說明如何運用雲端技術克服難題。 本課程是 Cloud Digital Leader 學習路徑的一部分,旨在促進個人職能發展,並打造企業的未來。
雲端技術是強大的資產,與資料搭配後,將成為創新和提升客戶體驗的催化劑。「運用 Google Cloud 探索資料轉換功能」課程將探討機構如何運用雲端,讓資料更易於存取、做為行動依據和更有價值。 這門課程是 Cloud Digital Leader 學習路徑的一部分,旨在協助個人在職務上成長,並打造企業的未來。