Shivam Shelke
成为会员时间:2025
钻石联赛
13560 积分
成为会员时间:2025
“生成式 AI 智能体:助力组织转型”是“Gen AI Leader”学习路线中的第五门课程,也是最后一门课程。本课程探讨了组织如何使用量身定制的生成式 AI 智能体,帮助应对特定的业务挑战。您将亲自动手构建一个基本的生成式 AI 智能体,并探索这些智能体的组成部分,例如模型、推理循环以及各种工具。
探索从任务驱动型工作流到以人为本的 AI 编排的重大转变。您将学习如何从战略层面区分增强和自动化,以及如何平衡机器效率与人类直觉。
完成入门级使用 Gemini Enterprise 编排多智能体工作流技能徽章课程,展示您在以下方面的技能:使用由 Gemini Enterprise 提供支持的智能体助理整合来自第一方和第三方来源的数据、制作多媒体营销材料,以及跨系统自动执行业务操作。 技能徽章通过动手实验和挑战赛形式的评估,检验您对特定产品的实际知识掌握情况。完成课程即可获得徽章,也可直接参加实验室挑战赛,快速获得徽章。徽章可证明您掌握技能的熟练程度,提升您的专业形象,最终助您获得更多职业机会。欢迎访问您的个人资料,跟踪您已获得的徽章。
Train more powerful models with a single GPU. In this course, you will learn how hardware can speed up model training and the key considerations when training models on a GPU. First, you will learn how to estimate the number of computations and the amount of computer memory required to train large neural networks. You will then discover techniques for reducing the computing and memory requirements when training a model. Techniques which you will apply for fine-tuning a Gemma model with 4 billion parameters. Finally, you will consider the potential environmental impacts of machine learning, with a focus on where questions of energy, water, and e-waste intersect with justice and equity.
This video covers how to use Gemini in Gmail to summarize emails, find information, and draft replies, helping you manage your inbox more efficiently.
This video covers how to eliminate tedious manual data entry using Gemini. Learn how to take a picture or screenshot of data (from PDFs, paper, or images) and prompt Gemini to instantly convert it into a structured Google Sheet. Discover this simple hack to save countless hours transcribing data, turning Gemini into your personal data entry assistant. Just snap, prompt, and export!
This video covers prompt engineering fundamentals for effective AI communication. Learn a simple framework (Persona, Task, Context, Format) to craft clear prompts, getting better, faster results from Gemini in Google Workspace. Discover how to use natural language, be specific, and iterate for optimal AI assistance.
In this video, you'll learn to create "what if" scenarios using AI's reasoning. You'll see how to set a "before" scene with a person holding a cake, prompt an action by asking "what would happen if they tripped?", and let the AI generate the plausible "after" image of the cake falling.
AI 推理是指利用经过训练的机器学习模型,通过应用其学习到的模式,对新的、未见过的数据进行预测的过程。本课程专为有兴趣在 Cloud Run 上快速部署 AI 推理服务的开发者、数据科学家和机器学习工程师而设计。对于熟悉基于云的无服务器应用部署解决方案,但可能没有使用 Google Cloud 无服务器产品运行 AI 推理经验的学员来说,本课程非常有用。 本课程包含使用 GPU 部署 AI 推理模型,以及将生成式 AI 应用与数据存储服务集成的示例。
这是一节入门级微课程,旨在解释什么是负责任的 AI、它的重要性,以及 Google 如何在自己的产品中实现负责任的 AI。此外,本课程还介绍了 Google 的 7 个 AI 开发原则。
This video covers how to use NotebookLM as a personal research assistant by adding sources, asking questions, and generating new content formats based on your documents.
In this Google DeepMind course you will learn how to prepare text data for language models to process. You will investigate the tools and techniques used to prepare, structure, and represent text data for language models, with a focus on tokenization and embeddings. You will be encouraged to think critically about the decisions behind data preparation, and what biases within the data may be introduced into models. You will analyze trade-offs, learn how to work with vectors and matrices, how meaning is represented in language models. Finally, you will practice designing a dataset ethically using the Data Cards process, ensuring transparency, accountability, and respect for community values in AI development.
完成本课程,赢取使用智能体开发套件 (ADK) 构建 AI 智能体中级技能徽章,展示您在以下方面的技能: 提出实际的语言模型研究问题;构建一个简单的词元化器;制作用于训练 Transformer 语言模型的数据集;运行小语言模型的训练循环。
This video covers five key ways to use Google's AI tools, including Gemini in Workspace, the Gemini app, and NotebookLM, to enhance your daily productivity.
This video covers how to build a personalized "Work with Me" agent using Gemini Gems, which helps streamline foundational feedback and makes your meetings more strategic and efficient.
使用 Google 的智能体开发套件 (ADK) 构建、配置和运行您的第一个 AI 智能体,将您对智能体的理解转化为实际应用。 在本实操课程中,您将设置一个完整的 ADK 开发环境,使用 Python 代码和 YAML 配置两种方式创建智能体,并通过多个界面运行智能体。您还将学习定义智能体行为的核心参数,将您在课程 1 中学到的知识应用到实际代码中。
了解如何使用智能体开发套件 (ADK) 构建可用于生产用途的复杂 AI 智能体。本课程介绍了 ADK 的开源框架,助力开发者从简单的提示工程跨越到代码优先的结构化软件开发方法,从而构建企业级多智能体系统。
本课程面向为组织配置 Gemini Code Assist 的 Google Cloud 开发者和 DevOps 工程师,需事先掌握 Google Cloud 控制台的基本知识。本课程介绍了 Gemini Code Assist 的优势,并比较了不同 Gemini Code Assist 版本的功能。本课程还介绍了如何在组织内配置和管理 Gemini Code Assist。
In this Google DeepMind course, you will learn the fundamentals of language models and gain a high-level understanding of the machine learning development pipeline. You will consider the strengths and limitations of traditional n-gram models and advanced transformer models. Practical coding labs will enable you to develop insights into how machine learning models work and how they can be used to generate text and identify patterns in language. Through real-world case studies, you will build an understanding around how research engineers operate. Drawing on these insights you will identify problems that you wish to tackle in your own community and consider how to leverage the power of machine learning responsibly to address these problems within a global and local context.
AI 智能体代表着超越传统大语言模型 (LLM) 的重大转变:AI 智能体不再仅仅只是生成基于文本的解决方案,更能自主行动来执行这些方案。 本课程将介绍 AI 智能体的基础知识、AI 智能体与 LLM API 的区别,以及 AI 智能体在现实世界中的价值所在。本课程基于 Google 的智能体白皮书,将为您提供必要的理论基础知识,以助您编写首行智能体代码 — 非常适合希望从自主、目标导向行为(而不仅仅是文本生成)的角度理解 AI 系统的开发者、架构师和技术决策者。 加入社区论坛,提出问题并参与讨论。
大致了解 AI 智能体的概念。了解 AI 智能体如何通过自主行动和推理来解决复杂问题。您将探索技术架构(模型、工具和编排),该架构使智能体能够学习、规划,并为您实现目标。
本课程能让机器学习从业者掌握评估生成式和预测式 AI 模型的基本工具、方法和最佳实践。要确保机器学习系统在实际运用中提供可靠、准确、高效的结果,做好模型评估至关重要。 学员将深入了解各项评估指标、方法及如何在不同模型类型和任务中适当应用这些指标和方法。课程将着重介绍生成式 AI 模型带来的独特挑战,并提供有效解决这些挑战的策略。通过利用 Google Cloud 的 Vertex AI Platform,学员可学习如何在模型选择、优化和持续监控工作中实施卓有成效的评估流程。
本课程致力于为您提供所需的知识和工具,让您能够了解 MLOps 团队在部署和管理生成式 AI 模型以及探索 Vertex AI 如何帮助 AI 团队简化 MLOps 流程时面临的独特挑战,并帮助您在生成式 AI 项目中取得成功。