Учасник із 2025
Transformer Models and BERT Model
Earned вер. 24, 2025 EDT
Encoder-Decoder Architecture
Earned вер. 23, 2025 EDT
Inspect Rich Documents with Gemini Multimodality and Multimodal RAG
Earned вер. 23, 2025 EDT
Create Embeddings, Vector Search, and RAG with BigQuery
Earned вер. 23, 2025 EDT
This course introduces you to the Transformer architecture and the Bidirectional Encoder Representations from Transformers (BERT) model. You learn about the main components of the Transformer architecture, such as the self-attention mechanism, and how it is used to build the BERT model. You also learn about the different tasks that BERT can be used for, such as text classification, question answering, and natural language inference.This course is estimated to take approximately 45 minutes to complete.
This course gives you a synopsis of the encoder-decoder architecture, which is a powerful and prevalent machine learning architecture for sequence-to-sequence tasks such as machine translation, text summarization, and question answering. You learn about the main components of the encoder-decoder architecture and how to train and serve these models. In the corresponding lab walkthrough, you’ll code in TensorFlow a simple implementation of the encoder-decoder architecture for poetry generation from the beginning.
Complete the intermediate Inspect Rich Documents with Gemini Multimodality and Multimodal RAG skill badge course to demonstrate skills in the following: using multimodal prompts to extract information from text and visual data, generating a video description, and retrieving extra information beyond the video using multimodality with Gemini; building metadata of documents containing text and images, getting all relevant text chunks, and printing citations by using Multimodal Retrieval Augmented Generation (RAG) with Gemini. Explore other content in the Gemini Enterprise Agent Ready (GEAR) program.
This course explores a Retrieval Augmented Generation (RAG) solution in BigQuery to mitigate AI hallucinations. It introduces a RAG workflow that encompasses creating embeddings, searching a vector space, and generating improved answers. The course explains the conceptual reasons behind these steps and their practical implementation with BigQuery. By the end of the course, learners will be able to build a RAG pipeline using BigQuery and generative AI models like Gemini and embedding models to address their own AI hallucination use cases.