Join

Generative AI courses

659 Courses

California Institute of Technology AWS Skill Builder

AWS で始める生成系 AI for Entry (Japanese ONLY) (Na) 日本語実写版

AWS で始める生成系 AI for Entry (Japanese ONLY) (Na) 日本語実写版 これから生成系 AI を業務で活用していく上で、そもそも生成系 AI とは何なのか、どのような技術的背景や、種類があり、業務で活用する上でのユースケースや課題を学習します。また、それらの課題に対して、AWS がどのように活用できるかを学習します。本コースは、AWS における生成系 AI の学習の第一歩.
course image
California Institute of Technology AWS Skill Builder

Introduction to Generative AI - Art of the Possible (Traditional Chinese)

Introduction to Generative AI - Art of the Possible (Traditional Chinese) 《Introduction to Generative AI - Art of the Possible》課程介紹了生成式 AI、使用案例、風險和優勢。藉助一個內容生成範例，我們對可能性藝術進行了說明。 本課程結束時，學員應該能夠描述生成式 AI 的基礎知識、風險和優勢。他們還應該能夠闡明如何在自己的企業中使用內容生成。 課程級別.
course image
California Institute of Technology AWS Skill Builder

Foundations of Prompt Engineering (Traditional Chinese)

Prompt工程基礎（繁體中文） 在本課程中，您將學到設計有效提示的原則、技巧和最佳實務。本課程將介紹提示工程設計的基礎知識，並隨著課程進展介紹進階提示技巧。您也會學習如何防範提示濫用，以及如何減輕與 FM 互動時的偏見。 課程等級：中級 持續時間：4 小時 注意：本課程具有本地化的註釋/字幕。旁白保留英語。 要顯示字幕，請按一下播放器右下角的 CC 按鈕.
course image
California Institute of Technology AWS Skill Builder

Foundations of Prompt Engineering (Simplified Chinese)

Prompt Engineering Foundations (Simplified Chinese) 在本课程中，您将学习设计有效提示的原则、技术和最佳实践。本课程将介绍提示工程的基本知识，然后逐步过渡到高级提示技术。您还将学习如何防止提示误用，以及如何在与基础模型 (FM, Foundation Model) 互动时减少偏差。 课程级别：中级 时长：4 小时 注意：本课程具有本地化的注释/字幕。旁白保留英语。要.
course image
California Institute of Technology AWS Skill Builder

Introduzione all'AI generativa - L'arte del possibile (Italiano) | Introduction to Generative AI - Art of the Possible (Italian)

Introduzione all'AI generativa - L'arte del possibile (Italiano) | Introduction to Generative AI - Art of the Possible (Italian) Il corso “Introduzione all'AI generativa - L'arte del possibile” fornisce un'introduzione all'AI, i casi d'uso, i rischi e i vantaggi. Con l'aiuto di un esempio di generazione di contenuti, illustreremo l'arte del possib.
course image
California Institute of Technology AWS Skill Builder

Planning a Generative AI Project (Korean)

Planning a Generative AI Project (Korean) Planning a Generative AI Project는 비즈니스 및 기술 의사 결정권자를 위한 생성형 AI Essentials라는 3부 시리즈의 두 번째 과정입니다. 아직 완료하지 않았다면 시리즈의 첫째 과정인 Introduction to Generative AI - Art of the Possible부터 시작하십시오. 이 과정에서는 생성형 인공 지능(AI)과 관련된 기술적 기본 사항.
course image
California Institute of Technology AWS Skill Builder

Build a Question-answering Bot using Generative AI (Traditional Chinese)

Build a Question-answering Bot using Generative AI (Traditional Chinese) 在此實驗室中，您將建置可回答 AWS 服務相關問題的 Chatbot。此實驗室的設計訴求是讓您實際體驗如何部署大型語言模型 (LLM)、將該模型與 Amazon Kendra 資料來源整合，以及建置可詢問 LLM 並使用檢索增強生成 (RAG) 來找出使用者問題解答的 Amazon Lex V2 Chatbot。此實驗室可協助您了解如何透過.
course image
California Institute of Technology AWS Skill Builder

Build a Question-answering Bot using Generative AI (Simplified Chinese)

建置基於生成式 AI 的問答機器人 (簡體中文) - AWS Skill Builder 在此實驗室中，您將建置可回答 AWS 服務相關問題的 Chatbot。此實驗室的設計訴求是讓您實際體驗如何部署大型語言模型 (LLM)、將該模型與 Amazon Kendra 資料來源整合，以及建置可詢問 LLM 並使用檢索增強生成 (RAG) 來找出使用者問題解答的 Amazon Lex V2 Chatbot。此實驗室可協助您了解.
course image
California Institute of Technology AWS Skill Builder

Build a Question-answering Bot using Generative AI (Korean)

Build a Question-answering Bot using Generative AI (Korean) 실습 개요 이 실습에서는 AWS 서비스에 대한 질문에 답변하는 챗봇을 빌드합니다. 이 실습은 대규모 언어 모델(LLM)을 배포하고, 이를 Amazon Kendra 데이터 원본과 통합하고, LLM을 쿼리하고 검색 증강 생성(RAG)을 통해 사용자 질문에 대한 답변을 찾는 Amazon Lex V2 챗봇을 빌드할 수 있는 실습 환경을 제공.
course image
California Institute of Technology AWS Skill Builder

Build a Question-answering Bot using Generative AI (Japanese)

Build a Question-answering Bot using Generative AI (Japanese) このラボでは、AWS のサービスに関する質問に答えるチャットボットを作成します。大規模言語モデル (LLM) のデプロイ、Amazon Kendra データソースとの統合、LLM にクエリを実行して検索拡張生成 (RAG) を使用する Amazon Lex V2 チャットボットの作成などの実践的な経験を提供します。このラボを通じて、言.
course image

A generative ai course is a fast-growing field of machine learning that can create new content, translate languages, write different types of creative content, and answer your questions in an informative way. It has great potential to revolutionize the way we create and use products.

A generative ai course refers to any artificial intelligence model that generates new data, information, or documents.

For example, many companies record their meetings, both live and virtual. Here are a few ways generative AI could transform these recordings:

And this is only a small part of all processes.

Generative AI Model Examples

There are a number of products using generative ai courses already available on the market – we'll give you a few examples below. The underlying principle of the generative ai courses at AI Eeducation varies depending on the specific model or algorithm used, but some common approaches include:

  1. Variational Autoencoders (VAEs) are a type of generative model that learns to encode input data into a latent space and then decode it back into the original data. The "variational" part of the name refers to the probabilistic nature of the latent space, allowing the model to generate a variety of outputs.

  2. Generative Adversarial Networks (GaN): GaNs consist of two neural networks, a generator and a discriminator, that are trained simultaneously through adversarial learning. The generator creates new data, and the discriminator evaluates how well the generated data matches the real data. The competition between the two networks causes the generator to improve over time in producing realistic outputs.

  3. Recurrent Neural Networks (RNNS) and Long Short-Term Memory (LSTM): These types of neural networks are often used to generate sequences such as text or music. RNNS and LSTM have memory that allows them to process a series of events over time, making them suitable for tasks where the order of elements is important.

  4. Transformer models: Transformer models, especially those with attention mechanisms, are very successful in various generative tasks. They can remember long-term dependencies and relationships in data, making them effective for tasks such as language translation and text generation.

  5. Autoencoders: Autoencoders consist of an encoder and a decoder, and they are trained to reconstruct the input data. Although they are primarily used for learning to represent and compress data, variations such as denoising autoencoders (e.g. in images) can be used for generative tasks.

An ai generative course involves feeding a model a large data set and optimizing its parameters to minimize the difference between the generated output and the real information. A model's ability to produce realistic and rich content depends on the complexity of its architecture, the quality and quantity of training data, and the optimization techniques used during training!