PyTorch is one of the most popular open source machine learning framework that accelerates the path from research to production deployment.

In this tutorial, Dmytro Dzhulgakov, core contributor for PyTorch, will go through an introductory level hands-on tutorial for building fashion recognizer.

Related links:

When you think of “deep learning” you might think of teams of PhDs with petabytes of data and racks of supercomputers.

But it turns out that a year of coding, high school math, a free GPU service, and a few dozen images is enough to create world-class models. fast.ai has made it their mission to make deep learning as accessible as possible.

In this interview fast.ai co-founder Jeremy Howard explains how to use their free software and courses to become an effective deep learning practitioner.

Learn More:

Alex Bocharov, Principal Researcher at Microsoft Quantum Systems group and Chris Granade, Senior Research Software Development Engineer join Vadim Karpusenko to discuss the impact of Quantum Computing on the Machine Learning and Artificial Intelligence domains.

Touching briefly on decade-old pioneering results in Quantum Machine Learning, the story switches to describe more recent technologies meant for near term generation of smaller “noisy” quantum computers. The second part of the interview showcases how you can get started using quantum machine learning with Q# and the QML library provided with the Microsoft Quantum Development Kit.

Time Index:

  • [00:10] – Introducing Alex Bocharov : intro into Quantum Computing
  • [02:16] – What is the time horizons for Quantum Neural Networks in practice?
  • [02:52] – Desirable properties of the variational quantum circuits
  • [06:00] – Introducing Chris Granade: How to use QC for ML/AI?
  • [06:50] – What does quantum development look like?
  • [08:45] – Do you need to learn Quantum gates to use Quantum Computing?
  • [11:05] – Executing Quantum code in Python Jupyter Notebook
  • [13:00] – Download is available at aka.ms/QML

More Information:

This epsisode of the AI Show talks about the new ML assisted data labeling capability in Azure Machine Learning Studio.

You can create a data labeling project and either label the data yourself, or take help of other domain experts to create labels for you. Multiple labelers can use browser based labeling tools and work in parallel.

As human labelers create labels, an ML model is trained in the background and its output is used to accelerate the data labeling workflow in various ways such as active learning, task clustering, and pre-labeling. Finally, you can export the labels in different formats.

Learn More:

This episode of the AI Show compares deep learning vs. machine learning.

You’ll learn how the two concepts compare and how they fit into the broader category of artificial intelligence. During this demo we will also describe how deep learning can be applied to real-world scenarios such as fraud detection, voice and facial recognition, sentiment analytics, and time series forecasting.

With Azure ML Pipelines, all the steps involved in the data scientist’s lifecycle can be stitched together in a single pipeline improving inner-loop agility, collaboration, and reuse of data and code, while maintaining high reliability.

This video explores Azure Machine Learning Pipelines, the end-to-end job orchestrator optimized for machine learning workloads.

Learn More:

The AI Show’s Favorite links:

In this episode of the AI Show, explore updates to the Azure Machine learning service model registry to provide more insights about your model.

Also, learn how you can deploy your models easily without going through the effort of creating additional driver and configuration files.

Learn More:

Related links: