Press "Enter" to skip to content

Category: Machine Learning

AI: Lying at Card Games via Probabilistic Modeling

Published 2022-12-06 by Kevin Feasel

Matt Eland is on a mission:

I taught an AI to lie at my favorite card game.

In this article, I’ll explore how I did that and what considerations I had to make while designing an artificial intelligence to play a social deduction-based card game. I’ll also discuss where the project is headed and the potential approaches that you might consider building game systems as an AI developer.

The game I chose to model is One Night Ultimate Werewolf by Bezier Games. This is a social deduction game modelled on the popular party games of Werewolf and Mafia. I’ll give you a quick overview of the rules in the next section, for those unfamiliar with it.

This is an interesting overview of the card game, as well as describing the project itself.

Comments closed

Multivariate Anomaly Detection with ADX

Published 2022-12-05 by Kevin Feasel

Adi Eldar shows off multivariate anomaly detection in Azure Data Explorer:

Azure Data Explorer (ADX) is commonly used for monitoring cloud resources and IoT devices performance and health. This is done by continuous collection of multiple metrics emitted by these sources, and on-going analysis of the collected data to detect anomalies. The analysis is applied over time series of the relevant metrics in order to locate significant deviations of the metrics values relative to their typical normal baseline pattern.

Click through for a nice overview of the topic, including two different scenarios: one which emphasizes time series data and the other, which does not.

Comments closed

Creating an AML Workspace and Trying the Studio

Published 2022-12-05 by Kevin Feasel

Tomaz Kastrun continues an advent of Azure ML. First up, Tomaz creates a workspace:

You will select “New workspace”. For now, we will work on a workspace. But just to mention, the “New registry” will enable you to share assets among different workspaces, support multi-region replication and help you provision all resources to facilitate region replications.

From there, the focus shifts to using Azure Machine Learning Studio:

In this overview page, you can click the button “Launch studio” in the middle of the workspace or you can copy and paste the Studio web URL provided under the “Essentials” to start the Studio.

But before we launch the Studio, let’s explore some additional settings, worth mentioning.

Comments closed

An Intro to Azure Machine Learning

Published 2022-12-02 by Kevin Feasel

Tomaz Kastrun has a new Advent challenge:

Azure Machine Learning (or Azure Machine Learning Service and abbreviation AML) is Azure’s cloud service for creating, managing and productionalising machine learning projects. It is a collaborative tool for Data Scientists, Machine Learning Engineers, and data engineers, covering their daily and operational tasks. From creating and training to deploying and managing predictive models and machine learning solutions.

Click through for the introduction.

Comments closed

The Problem of Reproducability in Neural Networks

Published 2022-12-01 by Kevin Feasel

Pete Warden explains a problem:

Last week I had a question from a colleague about reproducibility in TensorFlow, specifically in the 1.14 era. He wanted to be able to run the same training code multiple times and get exactly the same results, which on the surface doesn’t seem like an unreasonable expectation. Machine learning training is fundamentally a series of arithmetic operations applied repeatedly, so what makes getting the same results every time so hard? I had the same question when we first started TensorFlow, and I was lucky enough to learn some of the answers from the numerical programming experts on the team, so I want to share a bit of what I discovered.

Read on for that answer.

Comments closed

MLflow 2.0 Now Available

Published 2022-11-28 by Kevin Feasel

Mike Cornell announces MLflow 2.0:

Today, we are thrilled to announce the availability of MLflow 2.0. Building upon MLflow’s strong platform foundation, MLflow 2.0 incorporates extensive user feedback to simplify data science workflows and deliver innovative, first-class tools for MLOps. Features and improvements include extensions to MLflow Recipes (formerly MLflow Pipelines) such as AutoML, hyperparameter tuning, and classification support, as well modernized integrations with the ML ecosystem, a streamlined MLflow Tracking UI, a refresh of core APIs across MLflow’s platform components, and much more.

I like a lot of what MLflow does; it’ll be interesting to see how quickly different products adopt 2.0.

Comments closed

Working with Multi-Channel Bots in Azure

Published 2022-11-07 by Kevin Feasel

Matt Eland creates a mega-bot:

The Azure Bot Service is effectively a registration for a conversational AI application on Azure. This registration allows you to connect a deployed chatbots to a wide number of supported channels that users can use to interact with the bot.

This lets you build one bot that can serve a variety of users across multiple different channels, including both text and voice channels.

Additionally, the Azure Bot Service gives you a centralized place to manage, secure, and monitor your bot, regardless of which channel people use to interact with your app.

Read on for an important caveat, as well as more information on Azure Bot Service.

Comments closed

Pattern Learning in Amazon SageMaker

Published 2022-10-25 by Kevin Feasel

Vishaal Kapoor, et al, take us through an example of pattern learning in Amazon SageMaker:

Pattern learning automatically analyzes your data and surfaces textual constraints that may apply to your dataset. For the example with phone numbers, pattern learning can analyze the data and identify that the vast majority of phone numbers follow the textual constraint [1-9][0-9]{2}-[0-9][4]. It can also alert you that there are examples of invalid data so that you can exclude or correct them.

In the following sections, we demonstrate how to use pattern learning in Data Wrangler using a fictional dataset of product categories and SKU (stock keeping unit) codes.

Read on for the scenario.

Comments closed

Fine-Tuning Hugging Face for Named Entity Recognition in Japanese

Published 2022-10-24 by Kevin Feasel

Tsuyoshi Matsuzaki tries out a named entity recognition project with the Hugging Face library:

Now a lot of AI companies (such as, OpenAI, NLP Cloud, Google, NVIDIA, etc) are providing pre-trained large language models including methods that tune to enable models trained. Among such tools and framework, HuggingFace is widely used and providing over 20,000 transformer-based models.

In this post, I’ll show you brief fine-tuned example of transformer models in Hugging Face for your beginning.
In the last part of this post, I’ll also optimize training with DeepSpeed which is well integrated with HuggingFace transformers.

Click through for the results of this analysis.

Comments closed

Working with Transformer Models for Machine Translation

Published 2022-10-21 by Kevin Feasel

Stefania Cristina continues a series on transformer models. First up is plotting loss curves:

We have previously seen how to train the Transformer model for neural machine translation. Before moving on to inferencing the trained model, let us first explore how to modify the training code slightly, in order to be able to plot the training and validation loss curves that can be generated during the learning process. 

The training and validation loss values provide important pieces of information, because they allow us to have a better insight on how the learning performance is changing over the number of epochs, and help us diagnose any problems with learning that can lead to an underfit or an overfit model. They will also inform us about the epoch at which to use the trained model weights at the inferencing stage.

Then we get to try it out:

We have seen how to train the Transformer model on a dataset of English and German sentence pairs, as well as how to plot the training and validation loss curves in order to diagnose the model’s learning performance and decide at which epoch to inference the trained model. We are now ready to inference the trained Transformer model for the purpose of translating an input sentence.

In this tutorial, you will discover how to inference the trained Transformer model for neural machine translation. 

Click through for the results and to see exactly why there’s so much computational effort dumped into high-end trained models.

Comments closed