Filament-Syfter

Matt Maufe

Grounded Information Extraction and Semantic Search using Large Language Models

For many of us, Large Language Models (LLMs) no longer need any introduction, having taken the tech world by storm with offerings like…

7 min readJul 3, 2023

--

A side-by-side comparison of keyword search and extractive QA search. The question “What’s the difference between 401k and IRA” is asked in both. The keyword search on the left produces a series of results with highlighted terms from the question. The Extractive QA search on the right produces a single result that contains a paragraph from a relevant article, with the answer highlighted.

--

Dr James Ravenscroft

Challenges and Opportunities for Generative AI for Private Market Analysts

The recent wave of new generative AI solutions that leverage transformer-based large language models (LLMs) has injected renewed vigour and…

7 min readJun 13, 2023

--

Challenges and Opportunities for Generative AI for Private Market Analysts

--

Dr James Ravenscroft

What’s your ChatGPT Strategy? Updating Your Organisation’s AI Strategy in a Post-ChatGPT World

If you are a business leader or decision maker, you have probably heard of or tried out ChatGPT over the last few weeks. You might even…

6 min readDec 16, 2022

--

What’s your ChatGPT Strategy? Updating Your Organisation’s AI Strategy in a Post-ChatGPT World

--

Safa Abbas

Calibrating Machine Learning Models: What, Why and How?

Humans when making a statement or decision have a gauge of certainty, we use language to express how confident we are about what we are…

7 min readNov 11, 2022

--

Calibrating Machine Learning Models: What, Why and How?

--

Matt Maufe

Building Trust in your ML Models — Explainability

It’s important to be able to trust your model, especially if you’re making important decisions based on what it says, but how can we build…

12 min readOct 18, 2022

--

A diagram representing the transfer learning process with pre-trained models. There are three boxes labelled “Language Model”, “Fine tuning the model”, and “Final Model” left-to-right with arrows going from each box to the next. Above the first box is the text “Large corpus (like Wikipedia)” with an arrow pointing to the box. Above the second is the text “Task-specific dataset (like Q/A)” with an arrow. Above the second box is the text “Test dataset” with an arrow.

--

Ayesha Hafeez

An Introduction to Company Embeddings

— Authors: Ayesha Hafeez, Cynthia Masetto

7 min readMay 12, 2022

--

An Introduction to Company Embeddings

--

Dr James Ravenscroft

Painless Explainability for NLP/Text Models with LIME and ELI5

Introduction

19 min readMar 14, 2022

--

Painless Explainability for NLP/Text Models with LIME and ELI5

--

Dr James Ravenscroft

Serving NLP Models with MLFlow

MLFlow is a powerful open source MLOps platform with built in framework for serving your trained ML models as REST APIs. The REST…

8 min readDec 29, 2020

--

Serving NLP Models with MLFlow

--

Cynthia Masetto

Baking the perfect ML model

“…The application of deep neural networks remains a black art. Often requiring years of experience to effectively choose optimal…

11 min readSep 29, 2020

--

Baking the perfect ML model

--

Dr James Ravenscroft

How can AI practitioners reduce our carbon footprint?

In recent weeks and months the impending global climate catastrophe has been at the forefront of many peoples’ minds. Thanks to movements…

6 min readJun 20, 2019

--

1

How can AI practitioners reduce our carbon footprint?

--

1

From single machine learning models through to entire solutions — We are a trusted partner for organisations looking to deliver business value with AI.
Connect with Filament-Syfter
Editors
Phil Westcott
Dr James Ravenscroft
Ml and NLP Geek, CTO at Filament. Saxophonist, foodie and explorer. I was born in Bermuda and I Live in the UK
Tobin Sydneysmith
Head of Product Marketing @ Filament Syfter

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams