Stephen Strong
SAIC Lead Engineer / Architect of Edge Services Platform
Actions
40 years of software development / architecture focused on expressing engineering concepts visually through software. Providing consulting for Motorola, General Electric, Boeing, Booz Allen, SIAC and the US Government
Structured Knowledge Graphs that Unlock LLM Automation: A Low-Code .NET/Blazor Toolkit
Experience with Large Language Models like GPT4 has shown that it is difficult to execute complex multistep solutions. Knowledge graphs are a proven method for guiding chain-of-thought execution by LLMs.
Not all knowledge graphs are equally effective. We have developed a set of structured graphs that capture the context of the problem, organize the content, and guide the LLM to form a well-structured solution.
The talk demonstrates a powerful toolkit that allows domain experts and developers to collaborate on the creation of chain-of-thought solutions. The toolkit contains a low-code diagramming UI and a complementary API designed to integrate with Blazor applications. Once a structured knowledge graph is created using the open-source toolkit, it can be easily integrated into AI-centric solutions, including GPTs, copilots and AI assistants.
Common applications such as proposal generation, product configuration, and legal reasoning are used as examples.
.NET, IoT, Digital Twins and Defense - How SAIC uses .NET to field defense solutions quickly.
Join Steve Strong, Principal Software Architect at SAIC and Bryan Costanich, Cofounder/CEO of Wilderness labs as they take a deep dive into how SAIC uses .NET across a wide range of hardware and compute contexts to accelerate the adoption of cutting-edge technologies in defense.
Along the way, they’re going to examine how SAIC’s next generation of maintenance operations are powered by Meadow, Blazor, ASP.NET, and Azure to provide real-time insights into defense assets via IoT sensors that continuously monitor and feed data into the cloud to provide advanced visualization and analytics. With .NET, SAIC is reimagining what it means to instrument facilities and equipment, create a digital twin of those assets, and in turn, use AI and ML pipelines to generate design and operational insights that feed back into engineering and design to create more robust, adaptive, and reliable designs.
LA-MPS, an AI driven open-source solution to simplify legal research using Asp.net Core, Elastic Sea
We set out to create a resource for veterans suffering from PTSD and ended up building open-source legal research tools (LA-MPS), that can work across any legal domain. LA-MPS stands for Legal Apprentice, Marker, Pad, Search. The suite of tools makes it possible to train the AI for your personal legal apprentice on your desktop computer. The process, that works with as few as 20 labeled cases, can produce highly accurate case retrieval. A detailed discussion uses real examples taken from the Bureau of Veterans affairs.
A lawyer annotates the training set with Legal Marker. Marker generates annotated sentences and paragraphs from the original text in the form of json. The resulting enriched cases (now referred to as Legal Semantic json or ls-json). The ls-json data is used to train a TensorFlow classification model that is 80 % accurate with sentence classification in this domain. A pipeline is used to automatically enrich the remaining cases; in our example we did over 10,000. The ls-json cases are loaded into Legal Search for use by the team. An ASP.Net core solution provides the UI for Search which lets the team share notes in a Legal Pad application driven by SignalR. The results can be used to argue a specific case or return new annotations for the next round of training.
The process results in a very efficient way to extract findings, evidence and legal reasoning from a huge corpus of un-researched but relevant cases. Comparisons will be made with general tools like google search and CHAT-GPT4
Popular algorithms visualized
Gain understanding of algorithms like Quad-Tree, Force-Layout, Boids simulation, Machine Learning and Dijkstra's shortest route by seeing animations of these algorithms executing. It is a lot more fun than a code review.
Deep Dive into an Open-Source Blazor Library for Visualization and Simulation
Introducing an all-in-one native Blazor visualization library for diagramming, mapping and 3D visualization. This open-source library leverages popular drawing paradigms from Visio, Three.js, D3 JS, and CesiumJS to deliver an integrated C#/Blazor visualization capability.
During this session, I will cover concepts like 1D, 2D and 3D shapes, glue, scale drawings, maps, globes, and animation, and how I’ve implemented them using C#, Blazor and native web technologies like HTML5 canvas. I will show how I separate the presentation model from the data model, to make it easier to support multiple views of the data. I will also show how I used Blazor and SignalR to implement wide scale collaboration and drawing construction in both 2D and 3D environments over the Web.
The presentation will emphasize new features in Blazor and .NET 8 that contribute to web-based visualization and simulation. The open-source library will be available for attendees to use.
Stephen Strong
SAIC Lead Engineer / Architect of Edge Services Platform
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