In this learn module we will be learning how to do audio classification with TensorFlow. There are multiple ways to build an audio classification model. You can use the waveform, tag sections of a wave file, or even use computer vision on the spectrogram image. In this tutorial we will first break down how to understand audio data, from analog to digital representations, then we will build the model using computer vision on the spectrogram images. That's right, you can turn audio into an image representation and then do computer vision to classify the word spoken!

Use MLflow to track model metrics and artifacts when training and registering models with the Azure Machine Learning CLI (v2).

Like Fei Fei, use data to plan your own mission to the Moon. Ensure that your rocket can not only get you there, but also bring you and all your Moon rocks safely back to Earth.

Inspired by the new film Space Jam: A New Legacy, this learning path shows basketball fans how an understanding of data science and coding can support their passions, create opportunities, and even open doors to possible careers. Develop skills in Visual Studio Code, Azure, GitHub, JavaScript, and Python, to gain insights into how individual moments throughout a player's history can lead to a critical game decision in the finals.

Large-scale machine-learning and deep-learning models require ample compute power. Learn when to choose GPU compute, and how different frameworks help you to make optimal use of GPU compute during preprocessing, model training, and deployment.

Use the Azure Machine Learning CLI (v2) to deploy a machine learning model to a managed online endpoint.

Learn how to use concepts from machine learning to predict the occurrence of meteor showers (or Moon Goddess tears).

Learning to code sometimes feels out of reach. But if we've learned anything from the people who have burst through our atmosphere, orbited our Earth, or walked on the Moon, it's that goals that seem out of reach require determination and passion. In this learning path, we'll draw on these themes from the story line of Over the Moon.

The Azure Machine Learning CLI (v2) is an Azure CLI extension that you can use to train and deploy machine learning models. Learn how to use the CLI (v2) to create Azure Machine Learning workspace assets to use for model training and deployment.

Choose GPU compute in Azure Machine Learning when training compute-intensive models. To reduce the time needed to process the data, store your data efficiently and use a data manipulation library compatible with GPU compute.

In this module, we'll explore different neural network architectures for processing natural language texts. Natural Language Processing (NLP) has experienced fast growth and advancement primarily because the performance of the language models depends on their overall ability to "understand" text and can be trained using an unsupervised technique on large text corpora. Additionally, pre-trained text models (such as BERT) simplified many NLP tasks and has dramatically improved the performance. We'll learn more about these techniques and the basics of NLP in this learning module.

Explore the use of generative artificial intelligence (AI) models for natural language processing (NLP) in Azure Machine Learning.

This module provides all the concepts and practical knowledge you need to get started with TensorFlow. We explore Keras, a high-level API released as part of TensorFlow, and use it to build a simple neural network for image classification.

Train compute-intensive models with GPU compute in Azure Machine Learning. By monitoring workloads, you can find the optimal compute configuration. Distributed training allows you to train on multiple nodes to speed up training time.

Deploying large-scale models for real-time inferencing is challenging because of the model's size. Learn what you can do and which frameworks you can use to optimize your model's performance during model scoring.

Learn the fundamentals of deep learning with TensorFlow! This beginner friendly learning path will introduce key concepts to building machine learning models.

Learn how to automate and test model deployment with GitHub Actions and the Azure Machine Learning CLI (v2).

In this Learn module, you learn how to do audio classification with PyTorch. You'll understand more about audio data features and how to transform the sound signals into a visual representation called spectrograms. Then you'll build the model by using computer vision on the spectrogram images. That's right, you can turn audio into an image format, and then do computer vision to classify the word spoken!

Use JavaScript, Azure, GitHub, and Visual Studio Code to write a web app that helps the Tune Squad coach make data-based decisions on the basketball court, inspired by SPACE JAM: A NEW LEGACY.

Automate machine learning workflows with Azure Machine Learning pipelines, Azure Pipelines, and GitHub Actions.

Machine learning operations (MLOps) applies DevOps principles to machine learning projects. Learn about which DevOps principles help in scaling a machine learning project from experimentation to production.

If you've completed the first module and realized that you need extra flexibility to build or debug your model, then this module is for you. We'll show how you can create a simple neural network for image classification, but this time we'll use lower-level TensorFlow code and explain the foundational concepts needed to understand it.

This module explores different neural network architectures for dealing with natural language texts. Natural Language Processing (NLP) is growing in importance due to the ability of language models to accurately "understand" human language faster while using unsupervised training on large text corpora. This module covers different NLP techniques such as using bag-of-words (BoW), word embeddings and recurrent neural networks for classifying text from news headlines to one of the 4 categories (World, Sports, Business, and Sci-Tech).

Learn how to work with source control for your machine learning projects. Source control is an essential part of machine learning operations (MLOps).