16 results found
Part 1: Meet Atom Ai – the GPT Powering Innovation at WWT
This is the first article in a series exploring the technical foundations of Atom Ai (formerly WWT GPT), a GenAI-powered chatbot developed to increase employee productivity. It focuses on the purpose, scope, data sources and framework of WWT GPT as well as feedback and next steps.
Part 2: Inside Atom Ai – How Retrieval Mechanisms Shape AI Responses
This is the second article in a series exploring the technical foundations that power Atom Ai (formerly WWT GPT), a GenAI-powered chatbot developed to increase employee productivity. It focuses on the retrieval stage of the tool's RAG pipeline.
Part 3: Inside Atom Ai – How Generation Processes Enrich AI Conversations
This is the third article in a series exploring the technical foundations that power Atom Ai (formerly WWT GPT), a GenAI-powered chatbot developed to increase employee productivity. It explores how different generation processes impact AI conversations.
Part 2: Inside RFP Assistant — Summarizer and Qualification Workflow
The second article in a series exploring RFP Assistant, a GenAI-powered tool designed to increase the efficiency and impact of WWT's Proposal team. This article focuses on the tool's summarization, qualification and chat applications. Readers interested in LLM-powered generation, a RAG-powered chatbot and data science-powered insights will find value in how the combination of the three enables this tool.
Part 3: Inside RFP Assistant — Generating a Full RFP Response
The final article in a series exploring RFP Assistant, a GenAI-powered tool designed to increase the efficiency and impact of WWT's Proposal team. This article focuses on the tool's response generation capability. Readers interested in custom-built GenAI tools will learn how our tool takes a flexible amount of user input and utilizes our RAG to generate first-draft proposals.
Part 1: Meet RFP Assistant — the AI Improving Proposal Response Speed and Efficiency
In this first article in a series exploring RFP Assistant, you'll get an overview of the GenAI application we built in-house to streamline the proposal qualification and response process.
Automated Prompt Tuner (APT)
This report introduces Automated Prompt Tuner (APT), a framework that uses optimization techniques to refine prompts for large language models (LLMs), and demonstrates the application of APT to a request for proposal (RFP) text summarization use case.
Deep Learning With NVIDIA DGX-1
We highlight some practical considerations for the Deep Learning practitioner relevant to neural network training on the NVIDIA DGX-1.
MRI Radiomics: Tumor Identification and Reverse Image Search Using Convolutional Neural Network
This paper leverages deep learning to match MRI tumor images to scans with similar features with the goal of providing clinicians a tool to increase accuracy and speed to diagnosis.
Machine Learning Models for Route Consolidation
We develop a generalizable machine learning method for route consolidation. The developed method is compared against a more traditional ad-hoc method. The machine learning method uses a deep autoencoder, K-means clustering and Procrustes distance. The machine learning method is shown to produce similar results to the more traditional method with the advantage of using a more generalizable approach.
Image Classification of Race Cars
In this paper, we explore the use of artificial intelligence to perform an image sorting task to gain a competitive edge in a NASCAR race.
A New Use for Autoencoders in the Utility Industry
Learn how WWT experts are leveraging neural network autoencoders and k-means clustering to segment energy consumers based on meter reading data.