Charlie O'Neill – Medium

Charlie O'Neill

Pinned

Published in
TDS Archive

Can Transformers Learn to Strategize?

TicTacGPT for playing simple board games

Sep 8, 2023

Can Transformers Learn to Strategize?

Sep 8, 2023

Some quick thoughts on learning compressed representations and GPT-5 speculation

Language models are impressive, but I think they are cheating. We give them an abstract vocabulary as a way to compress the external world…

Mar 11, 2024

Mar 11, 2024

Published in
TDS Archive

Image Registration for Medical Datasets

From SimpleElastix to Spatial Transformer Networks

Feb 22, 2023

Image Registration for Medical Datasets

Feb 22, 2023

Published in
TDS Archive

Data analytics principles at an AI startup

Rules for a scientific approach to data analysis and machine learning

Sep 21, 2022

Data analytics principles at an AI startup

Sep 21, 2022

Published in
TDS Archive

Achieving state-of-the-art for offensive tweet prediction using transformers

Utilising DistilBERT and fine-tuning for text classification

May 2, 2022

Achieving state-of-the-art for offensive tweet prediction using transformers

May 2, 2022

Published in
TDS Archive

An introduction to transformers and Hugging Face

Leveraging the power of NLP from a top-down approach

Apr 26, 2022

An introduction to transformers and Hugging Face

Apr 26, 2022

Published in
TDS Archive

End-to-end Pytorch model in five minutes

Standardising dataloaders, model, training and validation — so you don’t have to

Feb 16, 2022

End-to-end Pytorch model in five minutes

Feb 16, 2022

Published in
TDS Archive

Using Deep Learning for Text-Generation of Wikipedia Articles

Using AWD-LSTMs for natural language models in fastai and Pytorch

Jan 27, 2022

Using Deep Learning for Text-Generation of Wikipedia Articles

Jan 27, 2022

Predicting the price of Bitcoin with multivariate Pytorch LSTMs

Using multivariate, multi-output forecasting models for financial data

Jan 25, 2022

Predicting the price of Bitcoin with multivariate Pytorch LSTMs

Jan 25, 2022

Published in
TDS Archive

Pytorch LSTMs for time-series data

Using the Pytorch functional API to build temporal models for univariate time-series

Jan 12, 2022

Pytorch LSTMs for time-series data

Jan 12, 2022

Charlie O'Neill

Charlie O'Neill

Researcher at Macuject, ANU. Interests include integration of deep learning, causal inference and meta-learning. Twitter: @charles0neill.

Following

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