Andy Cross

Andy Cross

CrossMoore Director, AI Entrepreneur

London, United Kingdom

Actions

Andy Cross has lead teams building the largest AI projects and deployments, hosted on Azure. He founded a consultancy in 2012 and grew it from 2 to 300 people. Along the way he has picked up quite a few interesting stories! He is co-founder of the UK London Azure User Group, formerly an Azure Most Valuable Professional and a Microsoft Regional Director.

Area of Expertise

  • Arts
  • Information & Communications Technology
  • Media & Information
  • Travel & Tourism

Topics

  • Azure
  • Software Design
  • Software
  • Generative AI

Over the Edge; Migration, Optimization and Intelligence for IoT devices with Microsoft Azure

What does a mature IoT Solution look like? Is it enough to just connect up to the cloud and go? What about my devices that can't speak Cloudy? How do I understand and control what this costs me? What about the promised AI that lives in the Cloud??

In this session, Andy introduces and explores the role of Edge devices in a modern IoT architecture and can be made intelligent.

There will be demos using Azure IoT tools, code, Cloud resources and simulated IoT Edge devices.

Preferred duration 60 minutes

Machine Learning with ML.NET and Azure Data Lake

ML.NET is an open source, machine learning framework built in .NET and runs on Windows, Linux and macOS. It allows developers to integrate custom machine learning into their applications without any prior expertise in developing or tuning machine learning models. Enhance your .NET apps with sentiment analysis, price prediction, fraud detection and more using custom models built with ML.NET

In this Session, Andy will show not only the core of ML.NET but best practices around Azure Data Lake and data in general when using .NET

Business Outcomes from AI

Andy Cross, Director of Elastacloud, Microsoft Regional Director, Azure MVP and all round good guy, gives a session on how to successfully build or transform a business using AI technologies.

Over the last years, Elastacloud have delivered analytics projects to a variety of customers. The greatest challenges around AI are both technical and organisational. The existing landscape of process and strategy doesn't solve these challenges in combination, and the gap between causes friction and the failure of AI projects.

When modelling the outcome of actions that were informed by AI, possibly enacted by AI, the standard risk modelling approaches need to be transformed to include a factor that can change over time to represent the effectiveness of the AI solutions. Given that we should accept errors as part of the AI solution, and that errors are reinforcing of better future decisions, we need to project risk as a decreasing vector over time.

Step into World Models

Every explanation of world models opens with a conditional probability, a subscript and a latent variable, and half the room has gone by the third slide. The core idea is much smaller than that. A world model answers one question: if things are like this and I do that, what happens next?

This talk builds one live, in TypeScript, around a single room with a heater. We start with forty hand-written lines, then throw the body away and fit four weights from 4,800 logged steps. Those four weights recover the room's physics and predict a day six degrees colder than anything in the logs. Then someone keeps opening a door that the logger never records. One private field, trained by walking each episode backwards, works out the door for itself, and the field turns out to be all "latent state" ever meant.

From there we put the model to work. I gave Claude the same room and it beat my model, until my model borrowed the shape of physics Claude described. A planner searches heater schedules against it, from a million brute-force guesses down to about a thousand with the cross-entropy method, replanning every step. Eight bootstrap copies draw a band showing where the model is unsure, and running the model beside the room makes it a fault monitor that catches a dead heater in sixteen readings. The field that found the door also hides a stuck heater, and I'll show how to catch that too.

You'll leave able to read the two equations the field rests on as a filter call, and with a clear sense of what the telemetry you already keep could do. Everything runs in a browser playground you can use during the session.

KEY TAKEAWAYS

1. Interleaved telemetry and commands are before-action-after records, which is exactly what a world model trains on. The labels are free because the next reading marks the homework.

2. The world model equation, the probability of the next state given the current state and action, is a WHERE clause with the SQL boiled off. The world model keeps that condition two values wide; an LLM's grows with the history, which is why LLMs are enormous.

3. A latent state is a private field the model fills for itself, judged only by the predictions it produces.

4. The shape of a model carries the knowledge that isn't in the log. A bias term the log can't tell apart from no bias sends a heater-off room 7.4 degrees colder than outside, and more rows of the wrong shape only make the wrong answer more confident.

5. An LLM and a world model are good at different things, and the useful pattern is to use both together.

6. A planner exploits a model's flaws, so a forecast should come with a band. The band maps where the uncertain weights matter, which isn't the same as where the data is thin.

7. A model that adapts quickly will explain some faults away. Watch what the model believes as well as what it gets wrong.

The talk is drawn from my blog series Understanding World Models at stepinto.dev, which builds the subject from runnable code rather than notation. All of the code is plain TypeScript with no ML libraries, and every model trains in under a second, so the demos run live in a browser and don't depend on GPUs or the venue's network once the page has loaded. The playground is public at stepinto.dev/heater/, so attendees can follow along on a laptop or phone.

The material comes from day-to-day work at Unimo, where we run telemetry and control for energy hardware in the field.

Series: https://stepinto.dev/series/understanding-world-models/
Playground: https://stepinto.dev/heater/

CloudBrew 2019 - A two-day Microsoft Azure event Sessionize Event

December 2019 Mechelen, Belgium

ITCamp 2019 Sessionize Event

June 2019 Cluj-Napoca, Romania

Andy Cross

CrossMoore Director, AI Entrepreneur

London, United Kingdom

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top