加入 登录

Kaloina RAKOTONARIVO

成为会员时间：2024

钻石联赛

35186 积分
Google DeepMind：训练小语言模型 Earned Jan 19, 2026 EST
Google DeepMind: 04 Discover The Transformer Architecture Earned Jan 19, 2026 EST
Google DeepMind: 03 Design And Train Neural Networks Earned Jan 18, 2026 EST
Google DeepMind: 02 Represent Your Language Data Earned Jan 17, 2026 EST
Google DeepMind: 01 Build Your Own Small Language Model Earned Jan 15, 2026 EST
融会贯通：为云数据分析师岗位做好准备 Earned Nov 18, 2025 EST
Production Machine Learning Systems Earned Feb 28, 2025 EST
ML Pipelines on Google Cloud Earned Feb 14, 2025 EST
利用 Vertex AI 实现机器学习运维 (MLOps)：模型评估 Earned Feb 13, 2025 EST
Google Cloud VMware Engine Fundamentals Earned Feb 7, 2025 EST
使用 BigQuery 创建嵌入、向量搜索和 RAG Earned Feb 5, 2025 EST
在 Google Cloud 上创建生成式 AI 应用 Earned Jan 22, 2025 EST
[Deprecated] Advanced ML: ML Infrastructure Earned Jan 22, 2025 EST
Introduction to Reliable Deep Learning Earned Jan 21, 2025 EST
Put It All Together: Prepare for a Cloud Data Analyst Job Earned Jul 26, 2024 EDT
通过 BigQuery ML 创建机器学习模型 Earned Jul 18, 2024 EDT
Data Catalog Fundamentals Earned Jul 17, 2024 EDT
在 Looker 中应用高级 LookML 概念 Earned Jul 5, 2024 EDT
Developing Data Models with LookML Earned Jun 7, 2024 EDT
适用于生成式 AI 的机器学习运维 (MLOps) Earned Jun 5, 2024 EDT
Vertex AI Studio 简介 Earned Jun 4, 2024 EDT
Analyzing and Visualizing Data in Looker Earned Apr 11, 2024 EDT
创建图片标注模型 Earned Mar 25, 2024 EDT
Transformer 模型和 BERT 模型 Earned Mar 22, 2024 EDT
编码器-解码器架构 Earned Mar 19, 2024 EDT
注意力机制 Earned Mar 15, 2024 EDT
Google Cloud 数据分析基础知识 Earned Mar 15, 2024 EDT
图像生成简介 Earned Mar 13, 2024 EDT
负责任的 AI 简介 Earned Mar 9, 2024 EST
生成式 AI 简介 Earned Mar 8, 2024 EST
大型语言模型简介 Earned Mar 6, 2024 EST

完成本课程，赢取 Google DeepMind：训练小语言模型高级技能徽章，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。 注册免费订阅，即可免费访问此实验。每月可免费获得 35 个点数！

了解详情

In this Google DeepMind course you will discover the mechanisms of the transformer architecture. You will investigate how transformer language models process prompts to make context-sensitive next-token predictions. Through practical activities you will explore the attention mechanism, visualize attention weights, and encounter advanced concepts like masked attention and multi-head attention. You will also learn other techniques that are necessary to build neural networks that are well-suited to be used as language models. Finally, through activities on values, stakeholder mapping and community engagement, you will practice concrete tools for ensuring AI projects are developed with communities, not just for them.

了解详情

In this Google DeepMind course you will focus on the training process for machine learning models. You will learn how to spot and mitigate issues when training a model, such as overfitting and underfitting. In practical coding labs, you will implement and evaluate the multilayer perceptron for simple classification tasks. This will provide insights into the mechanics of training a neural network model and the backpropagation algorithm. Research case studies will demonstrate how neural networks power real-world models. Additionally, you will consider the broader social impacts of innovation by looking beyond immediate benefits to anticipate potential risks, safety concerns, and further-reaching societal consequences.

了解详情

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.

了解详情

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.

了解详情

本课程是 Google Cloud 数据分析认证计划的第五门课程（共五门）。在本课程中，你将综合运用前 4 门课程所学的基础知识和技能，实操完成一个结业项目，全面探索整个数据生命周期。您将练习使用云端工具来有效地获取、存储、处理、分析、直观呈现数据并传达数据分析洞见。课程结束时，您将完成一个项目，证明您在以下方面的熟练程度：高效地设计数据结构以整理来自多个来源的数据、向不同利益相关方展示解决方案，以及使用云端软件直观呈现数据分析洞见。您还将更新个人简历并练习面试技巧，为求职申请与面试环节做好准备。

了解详情

This course covers how to implement the various flavors of production ML systems— static, dynamic, and continuous training; static and dynamic inference; and batch and online processing. You delve into TensorFlow abstraction levels, the various options for doing distributed training, and how to write distributed training models with custom estimators. This is the second course of the Advanced Machine Learning on Google Cloud series. After completing this course, enroll in the Image Understanding with TensorFlow on Google Cloud course.

了解详情

In this course, you will be learning from ML Engineers and Trainers who work with the state-of-the-art development of ML pipelines here at Google Cloud. The first few modules will cover about TensorFlow Extended (or TFX), which is Google’s production machine learning platform based on TensorFlow for management of ML pipelines and metadata. You will learn about pipeline components and pipeline orchestration with TFX. You will also learn how you can automate your pipeline through continuous integration and continuous deployment, and how to manage ML metadata. Then we will change focus to discuss how we can automate and reuse ML pipelines across multiple ML frameworks such as tensorflow, pytorch, scikit learn, and xgboost. You will also learn how to use another tool on Google Cloud, Cloud Composer, to orchestrate your continuous training pipelines. And finally, we will go over how to use MLflow for managing the complete machine learning life cycle.

了解详情

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。

了解详情

In this course, you will start by building a solid foundation in core Google Cloud VMware Engine (GCVE) concepts. From there, you'll dive into the unique architecture and components of GCVE, exploring how to prepare, deploy, and investigate VMs in a private cloud environment. The course will then guide you through managing and monitoring your private cloud, configuring networking and storage components, and connecting GCVE to the broader ecosystem of Google Cloud services and the internet.

了解详情

本课程探讨 BigQuery 中用于减轻 AI 幻觉的检索增强生成 (RAG) 解决方案。BigQuery 引入了 RAG 工作流，其中涵盖了创建嵌入、搜索向量空间和生成更优质的回答。本课程解释了这些步骤背后的概念原理，以及这些步骤在 BigQuery 中的实际实施过程。学完本课程后，学员将能够使用 BigQuery 和生成式 AI 模型（如 Gemini）以及嵌入模型来构建 RAG 流水线，以解决在具体情况下遇到的 AI 幻觉问题。

了解详情

生成式 AI 应用可以提供大语言模型 (LLM) 问世前几乎不可能实现的全新用户体验。作为应用开发者，您要如何利用生成式 AI 在 Google Cloud 上构建更具吸引力且功能强大的应用？ 在本课程中，您将了解生成式 AI 应用，以及如何利用提示设计和检索增强生成 (RAG) 技术，构建使用 LLM 的强大应用。您将了解可用于生产用途且适合生成式 AI 应用的架构，并构建一个基于 LLM 和 RAG 的聊天应用。

了解详情

Machine Learning is one of the most innovative fields in technology, and the Google Cloud Platform has been instrumental in furthering its development. With a host of APIs, Google Cloud has a tool for just about any machine learning job. In this advanced-level course, you will get hands-on practice with machine learning at scale and how to employ the advanced ML infrastructure available on Google Cloud.

了解详情

This course introduces you to the world of reliable deep learning, a critical discipline focused on developing machine learning models that not only make accurate predictions but also understand and communicate their own uncertainty. You'll learn how to create AI systems that are trustworthy, robust, and adaptable, particularly in high-stakes scenarios where errors can have significant consequences.

了解详情

This is the fifth of five courses in the Google Cloud Data Analytics Certificate. In this course, you’ll combine and apply the foundational knowledge and skills from courses 1-4 in a hands-on Capstone project that focuses on the full data lifecycle project. You’ll practice using cloud-based tools to acquire, store, process, analyze, visualize, and communicate data insights effectively. By the end of the course, you’ll have completed a project demonstrating their proficiency in effectively structuring data from multiple sources, presenting solutions to varied stakeholders, and visualizing data insights using cloud-based software. You’ll also update your resume and practice interview techniques to help prepare for applying and interviewing for jobs.

了解详情

完成中级技能徽章课程通过 BigQuery ML 创建机器学习模型，展示您在以下方面的技能： 使用 BigQuery ML 创建和评估机器学习模型，以执行数据预测。

了解详情

Data Catalog is deprecated and will be discontinued on January 30, 2026. You can still complete this course if you want to. For steps to transition your Data Catalog users, workloads, and content to Dataplex Catalog, see Transition from Data Catalog to Dataplex Catalog (https://cloud.google.com/dataplex/docs/transition-to-dataplex-catalog). Data Catalog is a fully managed and scalable metadata management service that empowers organizations to quickly discover, understand, and manage all of their data. In this quest you will start small by learning how to search and tag data assets and metadata with Data Catalog. After learning how to build your own tag templates that map to BigQuery table data, you will learn how to build MySQL, PostgreSQL, and SQLServer to Data Catalog Connectors.

了解详情

在本课程中，您将获得在 Looker 中应用高级 LookML 概念 的实践经验。您将学习如何使用 Liquid 自定义和创建动态 维度和测量、创建动态 SQL 派生表和自定义原生 派生表，并运用扩展功能来模块化你的 LookML 代码

了解详情

This course empowers you to develop scalable, performant LookML (Looker Modeling Language) models that provide your business users with the standardized, ready-to-use data that they need to answer their questions. Upon completing this course, you will be able to start building and maintaining LookML models to curate and manage data in your organization’s Looker instance.

了解详情

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。

了解详情

本课程介绍 Vertex AI Studio，这是一种用于与生成式 AI 模型交互、围绕业务创意进行原型设计并在生产环境中落地的工具。通过沉浸式应用场景、富有吸引力的课程和实操实验，您将探索从提示到产品的整个生命周期，了解如何将 Vertex AI Studio 用于多模态 Gemini 应用、提示设计、提示工程和模型调优。本课程的目的在于帮助您利用 Vertex AI Studio，在自己的项目中充分发掘生成式 AI 的潜力。

了解详情

In this course, you learn how to do the kind of data exploration and analysis in Looker that would formerly be done primarily by SQL developers or analysts. Upon completion of this course, you will be able to leverage Looker's modern analytics platform to find and explore relevant content in your organization’s Looker instance, ask questions of your data, create new metrics as needed, and build and share visualizations and dashboards to facilitate data-driven decision making.

了解详情

本课程教您如何使用深度学习来创建图片标注模型。您将了解图片标注模型的不同组成部分，例如编码器和解码器，以及如何训练和评估模型。学完本课程，您将能够自行创建图片标注模型并用来生成图片说明。

了解详情

本课程向您介绍 Transformer 架构和 Bidirectional Encoder Representations from Transformers (BERT) 模型。您将了解 Transformer 架构的主要组成部分，例如自注意力机制，以及该架构如何用于构建 BERT 模型。您还将了解可以使用 BERT 的不同任务，例如文本分类、问答和自然语言推理。完成本课程估计需要大约 45 分钟。

了解详情

本课程简要介绍了编码器-解码器架构，这是一种功能强大且常见的机器学习架构，适用于机器翻译、文本摘要和问答等 sequence-to-sequence 任务。您将了解编码器-解码器架构的主要组成部分，以及如何训练和部署这些模型。在相应的实验演示中，您将在 TensorFlow 中从头编写简单的编码器-解码器架构实现代码，以用于诗歌生成。

了解详情

本课程将向您介绍注意力机制，这是一种强大的技术，可令神经网络专注于输入序列的特定部分。您将了解注意力的工作原理，以及如何使用它来提高各种机器学习任务的性能，包括机器翻译、文本摘要和问题解答。

了解详情

了解如何在 Google Cloud 上将原始数字转化为清晰、以数据为依据的决策。通过实操实验和实际应用场景，本新手级课程将引导您在 BigQuery 中查询数据、在 Looker 中探索趋势，以及在数据洞察中制作可共享的交互式报告。

了解详情

本课程向您介绍扩散模型。这类机器学习模型最近在图像生成领域展现出了巨大潜力。扩散模型的灵感来源于物理学，特别是热力学。过去几年内，扩散模型成为热门研究主题并在整个行业开始流行。Google Cloud 上许多先进的图像生成模型和工具都是以扩散模型为基础构建的。本课程向您介绍扩散模型背后的理论，以及如何在 Vertex AI 上训练和部署此类模型。

了解详情

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。

了解详情

这是一节入门级微课程，旨在解释什么是生成式 AI、它的用途以及与传统机器学习方法的区别。该课程还介绍了可以帮助您开发自己的生成式 AI 应用的各种 Google 工具。

了解详情

这是一节入门级微学习课程，探讨什么是大型语言模型 (LLM)、适合的应用场景以及如何使用提示调整来提升 LLM 性能，还介绍了可以帮助您开发自己的 Gen AI 应用的各种 Google 工具。

了解详情