Understanding what your AI models are doing is super important both from a functional as well as ethical aspects. In this episode we will discuss what it means to develop AI in a transparent way.

Mehrnoosh introduces an awesome interpretability toolkit which enables you to use different state-of-the-art interpretability methods to explain your models decisions.

By using this toolkit during the training phase of the AI development cycle, you can use the interpretability output of a model to verify hypotheses and build trust with stakeholders.

You can also use the insights for debugging, validating model behavior, and to check for bias. The toolkit can even be used at inference time to explain the predictions of a deployed model to the end users.

Learn more:

In this episode, Luis shows how much more can really be done with Cognitive Search (with recipes to boot).

Extracting structure from unstructured data is a powerful addition to Cognitive Search!

His demo gives an amazing step-by-step process for using Cognitive search to enrich your index.

Main Demo starts at 4:56

LEARN MORE ABOUT KNOWLEDGE MINING:

The AI Show’s Favorite Links:

Machine Learning can be confusing sometimes.

From the esoteric terms to elevated expositions it seems like a terribly difficult area to get into.

Seth Juarez, like me, started off as a developer, and he tackles the one term that is used all of the time in Machine Learning: the elusive “model.

From the description:

First we set up how machine learning is different, how to think about it, and finally what a model actually is (spoiler alert – think “a function written a different way”). Would love your feedback

https://aka.ms/MachineLearningModels

Recently the Global AI Community held an AI night where Eric Boyd (Corporate Vice President of Azure AI) was the keynote speaker. Yours truly presented a session on Azure ML.

In this keynote, Eric Boyd shows us what makes Azure AI great for developers, gives behind the scenes stories, and teaches how you can get started with AI today.

For more information head over to http://aka.ms/AIDevResources

Some helpful resources:

n this episode of the AI Show Vinod Kurpad stops by to show a new surprising feature of Azure Search called the knowledge store.

The more I have explored Azure Search the more amazed I have been.

In this case Vinod presents an end to end walk through of how you can ingest, enrich, project and analyze your data using the knowledge store feature of Azure Search.

Show Summary


Learn More:

The AI Show’s Favorite Links:

Artificial Intelligence and Machine Learning are the latest in a long line of tech-worthy buzzwords.

Given the hype, it is often difficult to separate the technology from the marketing. Entrepreneurs need to understand what the technology actually does and the problems it solves.

In this talk by Seth Juarez, learn how AI and ML work, the kinds of problems it solves, and what the implications of its use are for your startup.

Armed with this practical knowledge, you’ll be able to make better decisions about where to start and how you can use machine learning and AI in your businesses.

For more information head over to https://aka.ms/aidevresources

Accelerate and optimize machine learning models regardless of training framework using ONNX and ONNX Runtime. This episode introduces both ONNX and ONNX Runtime and provides an example of ONNX Runtime accelerating Bing Semantic Precise Image Search.

Learn more about ONNX:

Follow ONNX on Social Media:

In this episode, learn how the Anomaly Detection service comes to your on-premises systems via containers.

By deploying the same API service close to your data in containers, now you don’t have to worry about situations when you have to keep the data on-premises to follow regulation, or to deal with network latency, or just want to reuse the same application powered-by Anomaly Detector across both the cloud and on-premise.

In this episode of the AI Show, get a look at a simple way to detect anomalies that can occur in your data.

Knowing when something goes off the rails is incredibly important and now easily done with a simple API call.

Azure Anomaly Detector Related Links