Fast Data Science and Harmony at Google with AI Camp on 10 Dec 2024

· Thomas Wood

Above: video of the AICamp meetup in London on 10 December 2024. Harmony starts at 40:00 - the first talk is by Connor Leahy of Conjecture

Tech Talk: GenAI and LLMs night at Google London on 10 December 2024

Fast Data Science presented the open source AI tool Harmony at recent GenAI and LLMs night at Google London on 10th December 2024 organised by AI Camp at Google Cloud Startup Hub.

AI Camp and Google co-hosted two deep dive tech talks on AI, GenAI, LLMs and machine learning, food/drink, networking with speakers and fellow developers.

The first talk of the evening was by Connor Leahy of Conjecture, titled “Cognitive Software and the (near) Future of AI”.

The second talk was given by Thomas Wood and Bettina Moltrecht, who presented our work on Harmony (harmonydata.ac.uk), a free online tool that uses generative AI and LLMs to help researchers discover datasets and compare items in questionnaires such as GAD-7 (used to measure anxiety), even when they are written in different languages. Harmony is open source under MIT License and is written in Python, and uses HuggingFace Sentence Transformers to find similarities between questionnaires. Harmony is funded by the Economic and Social Research Council and was previously funded by Wellcome.

Thomas Wood and Bettina Moltrecht presenting Harmony at AICamp at Google Startup Hub on 10 December 2024

Above: Thomas Wood and Bettina Moltrecht explain how sentence embeddings are used to map psychological questionnaire items to vectors of unit length on the surface of a hypersphere.

TopicHarmony, Open source AI tool for psychology research
SpeakersThomas Wood (Fast Data Science), Dr Bettina Moltrecht (UCL)
Date10th December 2024
Time6pm UK time
LocationGoogle Cloud Startup Hub, 4-5 Bonhill St., London
AbstractIn this talk, Thomas Wood and Bettina Moltrecht discuss using generative AI and LLMs to help researchers discover datasets and compare items in questionnaires such as GAD-7 (used to measure anxiety), even when they are written in different languages.

Missed the talk?

Download slides in PDF

Slide deck from Fast Data Science/Harmony AI and LLMs night at the Google Campus on 10 December 2024

Click to read more about AI in research at Fast Data Science.

Speaker profiles

Thomas Wood studied physics at university, and then did a masters in natural language processing in 2008. In 2018, he founded Fast Data Science, so he could work as a freelance consultant in natural language processing and machine learning. He is working as the industry partner on the Harmony project, and his other work includes applying natural language processing to clinical trial protocols.
Dr Bettina Moltrecht is a mental health researcher based at the University College London (UCL) and the Anna Freud National Centre for Children and Families in the UK. Bettina combines a strong clinical, tech and research background in her work.
Lorem Lorem

Short summary of the evening on LinkedIn

Final group photo

At the end of the evening, to wrap up the AICamp events of 2024, we took a group selfie! The organisers at AICamp later reported that they received good feedback from the talk’s attendees on the health theme: a lot found it to be on the right level, very much applied and a nice welcome to just having purely software focused talks.

Lorem

Find Top NLP Talent!

Looking for experts in Natural Language Processing? Post your job openings with us and find your ideal candidate today!

Post a Job

AI for financial advice
Generative ai

AI for financial advice

Financial advisors, like lawyers, are regulated in the UK. All financial advisors should be registered with the Financial Conduct Authority (FCA) and must have certain qualifications and have signed up to a code of ethics. UK financial advisors must also complete professional training every year.

How good are the best large language models in 2026?
Generative aiLegal ai

How good are the best large language models in 2026?

Which is the best AI for legal questions in 2026? We tested 16 Large Language Models (AIs) from the last two years on a law exam.

Should AI companies be allowed to mine creative content to train models?
Legal ai

Should AI companies be allowed to mine creative content to train models?

The effects of AI companies training on creative works When AI companies train models on text, video and images from creative industries, the end product is an AI model which can create near-human quality visual designs or copywriting. Many artists have argued the AI companies are exploiting creatives by profiting from their work, while the original creators do not receive any compensation. By flooding the market with low-cost content, AI has driven down rates for human artists, which is threatening creative careers.

What we can do for you

Transform Unstructured Data into Actionable Insights

Contact us