Iris Classon
Iris Classon - In Love with Code

Microsoft Ignite 2018 recap part 2: Artificial Intelligence

2018-10-11_18-42-28

Welcome to the second part of my Microsoft Ignite series! In this blog post I’ll cover news regarding Artificial Intelligence!

To read more about the blog post series, and where you can find all the videos:

Microsoft Ignite 2018 recap part 1: About MS Ignite and where to watch the sessions online

Azure AI consists of three main areas, AI Apps and Agents, Machine Learning and Knowledge Mining and announcements were made in all three areas. Most exciting for me as a wannabe data science nerd is the announcements in the two latter areas. Let’s talk about Azure ML first.

Automated Machine Learning and Hyperparameter Tuning

What

To create a ML model you need data, a training algorithm, and parameters (hyper parameters) that the algorithms take. The three ingredients make up the machine learning model after computations are done. Finding the right algorithms is tricky, and trying different parameters can be a tedious and slow process. With Automated ML in Azure you can set a few parameters, and then Azure ML will select the best (and efficient) algorithms to use as well as optimize model performance and select the best hyperparameters based on your target metric.

Read more

https://azure.microsoft.com/en-us/blog/announcing-automated-ml-capability-in-azure-machine-learning/

BRK3332 - Generating high quality models efficiently using Automated ML and Hyperparameter Tuning

https://myignite.techcommunity.microsoft.com/sessions/66245

Try it yourself

https://azure.microsoft.com/en-us/services/machine-learning-studio/

https://studio.azureml.net

 

Azure Machine Learning Python SDK

What

Core features of Azure Machine Learning are now accessible through a Python SDK that is easily installed with a pip install command. You can install just the SDK, or also additional features such as the automated ML feature I mentioned earlier. This means you can use the IDE of your choice to prepare data, work with the data, distribute across nodes and more.

Read more

https://docs.microsoft.com/en-us/python/api/overview/azure/ml/intro?view=azure-ml-py

THR2201 - Machine learning using Python in Azure Functions

https://myignite.techcommunity.microsoft.com/sessions/66640

THR3098 - AI TechTalk: Azure Machine Learning SDK - a walkthrough

https://myignite.techcommunity.microsoft.com/sessions/66265

Try it yourself

https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-train-models-with-aml

https://studio.azureml.net/

 

Azure Cognitive Services – Speech Service GA

What

Azure has a group of AI services, many of these came in preview earlier this year but are now in GA (General Availability).

These are the main areas: Visions, Knowledge, Language, Speech and Search. The Speech Service offers a variety of ways of working with speech and translation from an AI perspective and is now in GA. One thing in particular that is extra exciting is the Human Parity Text to Speech preview that makes text to speech sound more natural.

Sign up for the preview here: http://aka.ms/neuralttsintro

Read more

https://azure.microsoft.com/en-us/services/cognitive-services/speech-services/

THR2175 - AI TechTalk: What’s new in Cognitive Services speech recognition products

https://myignite.techcommunity.microsoft.com/sessions/66207?source=sessions

Try it yourself

Ready to run example:

https://github.com/IrisClasson/AzureExamples

Old blogpost on the topic:

http://irisclasson.com/2018/03/29/getting-started-with-azure-translator-api/

Create a free API key here:

https://azure.microsoft.com/en-us/try/cognitive-services/my-apis/?apiSlug=speech-services

 

 

Excel Enhancements

What

Excel has also undergone some significant AI enhancements, besides new functions that work with dynamic arrays (such as UNIQUE and FILTER). Two new AI feature have gotten a lot of attention, with the first one being the ‘Insert from Picture’ feature (currently in preview on Android). The feature lets the user use a photo of a data table, and have it inserted and transformed into an actual data table. Items that Excel is unsure of will be highlighted. The second feature is the new rich data types, stocks and geographies. When data is marked as one of the supported data types you will have access to the full rich data type model, including the properties. You will also have new graphs and graphics that are tied to the data type, for dynamic interaction with your data.

Read more

https://techcommunity.microsoft.com/t5/Excel-Blog/Preview-of-Stocks-and-Geography-New-Data-Types-in-Excel/ba-p/176185

https://www.microsoft.com/en-us/microsoft-365/blog/2018/09/24/10-new-ways-for-everyone-to-achieve-more-in-the-modern-workplace/

BRK3082 - Advanced analytics in Microsoft Excel: Get deep insights from your data including AI-powered capabilities

https://myignite.techcommunity.microsoft.com/sessions/64702

BRK2122 - What’s new in Microsoft Excel: Machine learning-powered insights, new data types, new visualizations, arrays, and more

https://myignite.techcommunity.microsoft.com/sessions/64644

THR1024 - Ten Excel features you’ll wish you’d known earlier

https://myignite.techcommunity.microsoft.com/sessions/64708

Try it yourself

Sign up to become an Office Insider

https://products.office.com/en/office-insider?tab=Windows-Desktop

Comments

Leave a comment below, or by email.


Last modified on 2018-10-10

comments powered by Disqus