Ruqiya Bin Safi
Membro dal giorno 2019
Membro dal giorno 2019
Questo corso ti introduce all'architettura Transformer e al modello BERT (Bidirectional Encoder Representations from Transformers). Scopri i componenti principali dell'architettura Transformer, come il meccanismo di auto-attenzione, e come viene utilizzata per creare il modello BERT. Imparerai anche le diverse attività per le quali può essere utilizzato il modello BERT, come la classificazione del testo, la risposta alle domande e l'inferenza del linguaggio naturale. Si stima che il completamento di questo corso richieda circa 45 minuti.
Questo corso ti introdurrà al meccanismo di attenzione, una potente tecnica che consente alle reti neurali di concentrarsi su parti specifiche di una sequenza di input. Imparerai come funziona l'attenzione e come può essere utilizzata per migliorare le prestazioni di molte attività di machine learning, come la traduzione automatica, il compendio di testi e la risposta alle domande.
Questo corso ti offre un riepilogo dell'architettura encoder-decoder, che è un'architettura di machine learning potente e diffusa per attività da sequenza a sequenza come traduzione automatica, riassunto del testo e risposta alle domande. Apprenderai i componenti principali dell'architettura encoder-decoder e come addestrare e fornire questi modelli. Nella procedura dettagliata del lab corrispondente, implementerai in TensorFlow dall'inizio un semplice codice dell'architettura encoder-decoder per la generazione di poesie da zero.
Questo è un corso di microlearning di livello introduttivo volto a spiegare cos'è l'IA responsabile, perché è importante e in che modo Google implementa l'IA responsabile nei propri prodotti. Introduce anche i 7 principi dell'IA di Google.
Questo è un corso di microlearning di livello introduttivo che esplora cosa sono i modelli linguistici di grandi dimensioni (LLM), i casi d'uso in cui possono essere utilizzati e come è possibile utilizzare l'ottimizzazione dei prompt per migliorare le prestazioni dei modelli LLM. Descrive inoltre gli strumenti Google per aiutarti a sviluppare le tue app Gen AI.
Welcome Gamers! Learn the fundamentals of BQML, all while having fun! In this game, you will learn to use the python-based command line tool for BigQuery. The hands-on labs will help you create a machine learning model, a classification model, and a forecasting model. Earn the points by completing the steps in the lab... Be sure to click "End" when you're done with each lab to get the maximum points. All players will be awarded the game badge.
Questo è un corso di microlearning di livello introduttivo volto a spiegare cos'è l'AI generativa, come viene utilizzata e in che modo differisce dai tradizionali metodi di machine learning. Descrive inoltre gli strumenti Google che possono aiutarti a sviluppare le tue app Gen AI.
In the last installment of the Dataflow course series, we will introduce the components of the Dataflow operational model. We will examine tools and techniques for troubleshooting and optimizing pipeline performance. We will then review testing, deployment, and reliability best practices for Dataflow pipelines. We will conclude with a review of Templates, which makes it easy to scale Dataflow pipelines to organizations with hundreds of users. These lessons will help ensure that your data platform is stable and resilient to unanticipated circumstances.
In this second installment of the Dataflow course series, we are going to be diving deeper on developing pipelines using the Beam SDK. We start with a review of Apache Beam concepts. Next, we discuss processing streaming data using windows, watermarks and triggers. We then cover options for sources and sinks in your pipelines, schemas to express your structured data, and how to do stateful transformations using State and Timer APIs. We move onto reviewing best practices that help maximize your pipeline performance. Towards the end of the course, we introduce SQL and Dataframes to represent your business logic in Beam and how to iteratively develop pipelines using Beam notebooks.
This course is part 1 of a 3-course series on Serverless Data Processing with Dataflow. In this first course, we start with a refresher of what Apache Beam is and its relationship with Dataflow. Next, we talk about the Apache Beam vision and the benefits of the Beam Portability framework. The Beam Portability framework achieves the vision that a developer can use their favorite programming language with their preferred execution backend. We then show you how Dataflow allows you to separate compute and storage while saving money, and how identity, access, and management tools interact with your Dataflow pipelines. Lastly, we look at how to implement the right security model for your use case on Dataflow.
L'integrazione del machine learning nelle pipeline di dati aumenta la capacità di estrarre insight dai dati. Questo corso illustra i modi in cui il machine learning può essere incluso nelle pipeline di dati su Google Cloud. Per una personalizzazione minima o nulla, il corso tratta di AutoML. Per funzionalità di machine learning più personalizzate, il corso introduce Notebooks e BigQuery Machine Learning (BigQuery ML). Inoltre, il corso spiega come mettere in produzione soluzioni di machine learning utilizzando Vertex AI.
L'elaborazione dei flussi di dati sta diventando sempre più diffusa poiché la modalità flusso consente alle aziende di ottenere parametri in tempo reale sulle operazioni aziendali. Questo corso tratta la creazione di pipeline di dati in modalità flusso su Google Cloud. Pub/Sub viene presentato come strumento per la gestione dei flussi di dati in entrata. Il corso spiega anche come applicare aggregazioni e trasformazioni ai flussi di dati utilizzando Dataflow e come archiviare i record elaborati in BigQuery o Bigtable per l'analisi. Gli studenti acquisiranno esperienza pratica nella creazione di componenti della pipeline di dati in modalità flusso su Google Cloud utilizzando QwikLabs.
Complete the intermediate Engineer Data for Predictive Modeling with BigQuery ML skill badge to demonstrate skills in the following: building data transformation pipelines to BigQuery using Dataprep by Trifacta; using Cloud Storage, Dataflow, and BigQuery to build extract, transform, and load (ETL) workflows; and building machine learning models using BigQuery ML. A skill badge is an exclusive digital badge issued by Google Cloud in recognition of your proficiency with Google Cloud products and services and tests your ability to apply your knowledge in an interactive hands-on environment. Complete the skill badge course, and final assessment challenge lab, to receive a digital badge that you can share with your network.
Le pipeline di dati in genere rientrano in uno dei paradigmi EL (Extract, Load), ELT (Extract, Load, Transform) o ETL (Extract, Transform, Load). Questo corso descrive quale paradigma dovrebbe essere utilizzato e quando per i dati in batch. Inoltre, questo corso tratta diverse tecnologie su Google Cloud per la trasformazione dei dati, tra cui BigQuery, l'esecuzione di Spark su Dataproc, i grafici della pipeline in Cloud Data Fusion e trattamento dati serverless con Dataflow. Gli studenti fanno esperienza pratica nella creazione di componenti della pipeline di dati su Google Cloud utilizzando Qwiklabs.
Complete the intermediate Build a Data Warehouse with BigQuery skill badge to demonstrate skills in the following: joining data to create new tables, troubleshooting joins, appending data with unions, creating date-partitioned tables, and working with JSON, arrays, and structs in BigQuery. A skill badge is an exclusive digital badge issued by Google Cloud in recognition of your proficiency with Google Cloud products and services and tests your ability to apply your knowledge in an interactive hands-on environment. Complete the skill badge course, and final assessment challenge lab, to receive a digital badge that you can share with your network. For practice with BigQuery fundamentals (including working with the console and command line), complete the course titled BigQuery Basics for Data Analysts.
Complete the introductory Prepare Data for ML APIs on Google Cloud skill badge to demonstrate skills in the following: cleaning data with Dataprep by Trifacta, running data pipelines in Dataflow, creating clusters and running Apache Spark jobs in Dataproc, and calling ML APIs including the Cloud Natural Language API, Google Cloud Speech-to-Text API, and Video Intelligence API. A skill badge is an exclusive digital badge issued by Google Cloud in recognition of your proficiency with Google Cloud products and services and tests your ability to apply your knowledge in an interactive hands-on environment. Complete this skill badge course, and the final assessment challenge lab, to receive a skill badge that you can share with your network.
Questo corso presenta i prodotti e i servizi per big data e di machine learning di Google Cloud che supportano il ciclo di vita dai dati all'IA. Esplora i processi, le sfide e i vantaggi della creazione di una pipeline di big data e di modelli di machine learning con Vertex AI su Google Cloud.
I due componenti chiave di qualsiasi pipeline di dati sono costituiti dai data lake e dai data warehouse. In questo corso evidenzieremo i casi d'uso per ogni tipo di spazio di archiviazione e approfondiremo i dettagli tecnici delle soluzioni di data lake e data warehouse disponibili su Google Cloud. Inoltre, descriveremo il ruolo di un data engineer, illustreremo i vantaggi di una pipeline di dati di successo per le operazioni aziendali ed esamineremo i motivi per cui il data engineering dovrebbe essere eseguito in un ambiente cloud. Questo è il primo corso della serie Data Engineering on Google Cloud. Dopo il completamento di questo corso, iscriviti al corso Building Batch Data Pipelines on Google Cloud.
This course helps learners create a study plan for the PDE (Professional Data Engineer) certification exam. Learners explore the breadth and scope of the domains covered in the exam. Learners assess their exam readiness and create their individual study plan.
In this quest you will use several tools available in Google Cloud to manipulate data and create a Google Map - map location details to find subway stations or a business; use geocoding and Apps Script to send an email of a map; visualize data on a customized map; and build a server-side proxy to create a map on a mobile device.
Workspace is Google's collaborative applications platform, delivered from Google Cloud. In this introductory-level course you will get hands-on practice with Workspace’s core applications from a user perspective. Although there are many more applications and tool components to Workspace than are covered here, you will get experience with the primary apps: Gmail, Calendar, Sheets and a handful of others. Each lab can be completed in 10-15 minutes, but extra time is provided to allow self-directed free exploration of the applications.
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, GCP has a tool for just about any machine learning job. In this advanced-level quest, you will get hands-on practice with machine learning at scale and how to employ the advanced ML infrastructure available on GCP.
TensorFlow is an open source software library for high performance numerical computation that's great for writing models that can train and run on platforms ranging from your laptop to a fleet of servers in the Cloud to an edge device. This quest takes you beyond the basics of using predefined models and teaches you how to build, train and deploy your own on Google Cloud.
It’s no secret that machine learning is one of the fastest growing fields in tech, and the Google Cloud Platform has been instrumental in furthering its development. With a host of APIs, GCP has a tool for just about any machine learning job. In this introductory quest, you will get hands-on practice with machine learning as it applies to language processing by taking labs that will enable you to extract entities from text, and perform sentiment and syntactic analysis as well as use the Speech to Text API for transcription.
Using large scale computing power to recognize patterns and "read" images is one of the foundational technologies in AI, from self-driving cars to facial recognition. The Google Cloud Platform provides world class speed and accuracy via systems that can utilized by simply calling APIs. With these and a host of other APIs, GCP has a tool for just about any machine learning job. In this introductory quest, you will get hands-on practice with machine learning as it applies to image processing by taking labs that will enable you to label images, detect faces and landmarks, as well as extract, analyze, and translate text from within images.
This advanced-level quest is unique amongst the other catalog offerings. The labs have been curated to give IT professionals hands-on practice with topics and services that appear in the Google Cloud Certified Professional Data Engineer Certification. From Big Query, to Dataprep, to Cloud Composer, this quest is composed of specific labs that will put your Google Cloud data engineering knowledge to the test. Be aware that while practice with these labs will increase your skills and abilities, you will need other preparation, too. The exam is quite challenging and external studying, experience, and/or background in cloud data engineering is recommended. Looking for a hands on challenge lab to demonstrate your skills and validate your knowledge? On completing this quest, enroll in and finish the additional challenge lab at the end of the Engineer Data in the Google Cloud to receive an exclusive Google Cloud digital badge.
Big data, machine learning, and artificial intelligence are today’s hot computing topics, but these fields are quite specialized and introductory material is hard to come by. Fortunately, Google Cloud provides user-friendly services in these areas, and with this introductory-level quest, so you can take your first steps with tools like Big Query, Cloud Speech API, and AI Platform. Want extra help? 1-minute videos walk you through key concepts for each lab.
It's no secret that machine learning is one of the fastest growing fields in tech, and Google Cloud 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 quest, you will get hands-on practice with machine learning APIs by taking labs like Detect Labels, Faces, and Landmarks in Images with the Cloud Vision API. Looking for a hands-on challenge lab to demonstrate your skills and validate your knowledge? On completing this quest, enroll in and finish the additional challenge lab at the end of this quest to receive an exclusive Google Cloud digital badge.
In this introductory-level Quest, you will get hands-on practice with the Google Cloud’s fundamental tools and services. Google Cloud Essentials is the recommended first Quest for the Google Cloud learner - you will come in with little or no prior cloud knowledge, and come out with practical experience that you can apply to your first Google Cloud project. From writing Cloud Shell commands and deploying your first virtual machine, to running applications on Kubernetes Engine or with load balancing, Google Cloud Essentials is a prime introduction to the platform’s basic features. 1-minute videos walk you through key concepts for each lab.