参加 ログイン

Sarda Sanjeev

メンバー加入日: 2025

ダイヤモンド リーグ

46415 ポイント
Google DeepMind: 小規模言語モデルのトレーニング Earned 4月 11, 2026 EDT
Google DeepMind: 07 Accelerate Your Model Earned 4月 10, 2026 EDT
Google DeepMind: 05 Fine-Tune Your Model Earned 4月 10, 2026 EDT
Google DeepMind: 04 Discover The Transformer Architecture Earned 4月 10, 2026 EDT
Google DeepMind: 03 Design And Train Neural Networks Earned 4月 8, 2026 EDT
Google DeepMind: 02 Represent Your Language Data Earned 4月 8, 2026 EDT
Google DeepMind: 01 Build Your Own Small Language Model Earned 4月 8, 2026 EDT
How to Use TPUs for Inference Earned 4月 7, 2026 EDT
Architecting an AI Inference Stack Earned 4月 7, 2026 EDT
最初のエージェントをデプロイする Earned 3月 28, 2026 EDT
[DEPRECATED] Orchestrate Complex Multi-Agent Workflows Earned 3月 28, 2026 EDT
Coordinate Multiple Agents Earned 3月 28, 2026 EDT
Hybrid Cloud Multi-Cluster with Anthos Earned 2月 15, 2025 EST
Hybrid Cloud Service Mesh with Anthos Earned 2月 9, 2025 EST
Hybrid Cloud Infrastructure Foundations with Anthos Earned 2月 8, 2025 EST
Google Kubernetes Engine の費用の最適化 Earned 2月 7, 2025 EST
Google Cloud での Kubernetes アプリケーションのデプロイ Earned 2月 6, 2025 EST
Compute Engine での Cloud Load Balancing の実装 Earned 2月 1, 2025 EST
Google Kubernetes Engine を使用した構築: 実践 Earned 1月 31, 2025 EST
Google Kubernetes Engine を使用した構築: ワークロード Earned 1月 25, 2025 EST
Google Kubernetes Engine を使用した構築: 基礎 Earned 1月 19, 2025 EST
Google Cloud の基礎: コア インフラストラクチャ Earned 1月 18, 2025 EST

上級コース「Google DeepMind: 小規模言語モデルのトレーニング」を修了してスキルバッジを獲得すると、以下のスキルを習得したことを 証明できます。現実世界の言語モデルにおける研究課題の策定、簡単なトークナイザーの構築、Transformer 言語モデルのトレーニング用データセットの準備、 小規模言語モデルのトレーニング ループの実行といったスキルを実証できます。無料 サブスクリプションに登録すると、このラボに無料でアクセスできます。また、毎月 35 クレジットを無料で受け取れます。

詳細

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.

詳細

Unleash the power of language models with fine-tuning. In this course, you will learn how to adjust a pre-trained model to a specific task. You will start with full-parameter fine-tuning using a small language model. To tune larger models like Gemma, you will learn parameter-efficient techniques with a focus on LoRA. Finally, you will be briefly introduced to reinforcement learning as an alternative to supervised fine-tuning (SFT). You will also explore how AI is imagined and made sense of in cultural contexts. You will consider why responsible AI is not just about technical safety but also about building governance systems that reflect community values and protect the public interest.

詳細

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.

詳細

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.

詳細

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.

詳細

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.

詳細

This course is for developers interested in learning how to use TPUs for inference—from architecture to deployment, and how to solve common implementation challenges.

詳細

This course is designed for developers looking to build an optimized AI inference stack on Google Cloud. Whether you’re working with GPUs or TPUs, you’ll explore the fundamental components of an inference stack, learn design principles for maximizing performance and reliability, and explore practical techniques to take your workloads from 0 to 1.

詳細

エージェントを localhost から本番環境に移行します。このコースでは、ADK エージェントを Vertex AI Agent Engine と Cloud Run にデプロイする方法を学びます。メモリバンクを使用するセッション間メモリについても、任意で受講できます。

詳細

Learn to orchestrate complex multi-agent workflows. This lesson teaches you to choose the right workflow patterns, manage state across agents, understand when custom logic is needed, and introduces distributed agent systems with A2A Protocol.

詳細

Learn to coordinate multiple specialized agents working together. This lesson teaches you when to use multi-agent systems, how to orchestrate agents with workflow patterns, and how agents communicate through shared state. By the end, you’ll build a complete multi-agent application.

詳細

This on-demand course equips students to understand, configure, and maintain multi-cluster Kubernetes infrastructures using Anthos GKE, and Istio-based service mesh, whether deployed with Anthos on Google Cloud or with Anthos deployed on VMware. This is the third, and final, course of the Architecting Hybrid Cloud Infrastructure with Anthos series. Completion of the Architecting with Google Kubernetes Engine path is a prerequisite for this course.

詳細

This on-demand course equips students to understand and adopt Istio-based service-mesh with Anthos for centralized observability, traffic management, and service-level security. This is the second course of the Architecting Hybrid Cloud Infrastructure with Anthos series. After completing this course, learners should continue to the Hybrid Cloud Multi-Cluster with Anthos course. Completion of the Architecting with Google Kubernetes Engine path is a prerequisite for this course.

詳細

Welcome to Hybrid Cloud Infrastructure Foundations with Anthos! This is the first course of the Architecting Hybrid Cloud Infrastructure with Anthos path. Anthos enables you to build and manage modern applications, and gives you the freedom to choose where to run them. Anthos gives you one consistent experience in both your on-premises and cloud environments. During this course, you will be presented with modules that will take you through skills that you will use as an architect or administrator running Anthos environments. The modules in this course include videos, hands-on labs, and links to helpful documentation.

詳細

「Google Kubernetes Engine の費用の最適化」の中級スキルバッジを獲得すると、 マルチテナント クラスタの作成と管理、各 Namespace のリソース使用状況のモニタリング、 効率向上のためのクラスタと Pod の自動スケーリングの構成、最適なリソース配分のためのロード バランシングの設定、 アプリケーションの健全性と費用対効果を確保するための liveness プローブと readiness プローブの実装といったスキルを実証できます。

詳細

Google Cloud での Kubernetes アプリケーションのデプロイ コースの中級スキルバッジを獲得できるアクティビティを修了すると、 Docker コンテナ イメージの構成とビルド、Google Kubernetes Engine（GKE）クラスタの作成と管理、kubectl を活用した効率的な クラスタ管理、堅牢な継続的デリバリー（CD）による Kubernetes アプリケーションのデプロイ手法といったスキルを実証できます。

詳細

「Compute Engine での Cloud Load Balancing の実装」入門コースを修了してスキルバッジを獲得すると、次のスキルを実証できます: Compute Engine における仮想マシンの作成とデプロイ、 ネットワーク ロードバランサとアプリケーション ロードバランサの構成。

詳細

このコースでは、Kubernetes と Google Kubernetes Engine（GKE）のセキュリティについて、およびロギングとモニタリングについて学びます。また、Google Cloud マネージド ストレージ サービスとデータベース サービスを GKE 内で使用する方法についても学びます。 これは「Google Kubernetes Engine を使用した構築」シリーズの 2 つ目のコースです。このコースを修了したら、「信頼性に優れた Google Cloud インフラストラクチャ: 設計とプロセス」コースか、「Hybrid Cloud Infrastructure Foundations with Anthos」コースに登録してください。

詳細

「Google Kubernetes Engine を使用した構築: ワークロード」を履修することで、クラウドネイティブ アプリケーション開発のすべてを網羅した取り組みに着手することができるようになります。学習体験全体を通して、Kubernetes オペレーション、デプロイ管理、GKE ネットワーキング、永続ストレージについて詳しく学びます。 これは「Google Kubernetes Engine を使用した構築」シリーズの最初のコースです。このコースを修了したら、「Google Kubernetes Engine を使用した構築: 実践」コースに登録してください。

詳細

このコース「Google Kubernetes Engine を使用した構築: 基礎」では、Google Cloud の全体像と基本的な考え方を確認した後、ソフトウェア コンテナを作成して管理する方法と Kubernetes のアーキテクチャについて説明します。

詳細

Google Cloud の基礎: コア インストラクチャ では、Google Cloud に関する重要なコンセプトと用語について説明します。このコースでは動画とハンズオンラボを通じて学習を進めていきます。Google Cloud の多数のコンピューティング サービスとストレージ サービス、そしてリソースとポリシーを管理するための重要なツールについて比較しながら説明します。

詳細