Thomas Wood presents the Harmony project at the 19th AI and Deep Learning for Enterprise meetup on 8 October 2024.
In case you missed the talk about Harmony on Tuesday at Civo Tech Junction with AI and Deep Learning for Enterprise sponsored by Daemon, you can now watch the recording of the live stream on AI|DL’s channel.
Topic: Harmony: a free online tool using LLMs for research in psychology and social sciences
Speaker: Thomas Wood (Fast Data Science)
Description: Thomas Wood will present our work on Harmony, harmonydata.ac.uk, which is a free online tool that uses generative AI and LLMs to help researchers 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 Discovery will soon allow researchers to discover datasets using a vector search.
Location: Civo Tech Junction, First Floor, 32-37 Cowper St, London EC2A 4AW
Date: 8 October 2024
The other speakers include:
The AI|DL AI meetup is sponsored by Daemon.
06:30pm - Doors open, food and drink served
07:00pm - Welcome
07:05pm - A short talk from our hosts Daemon
07:10pm - Thomas Wood, Director of Fast Data Science Project Harmony: a free online tool using LLMs for research in psychology and social sciences
Thomas Wood will present our work on Harmony (harmonydata.ac.uk), which is a free online tool that uses generative AI and LLMs to help researchers 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 will soon allow researchers to discover datasets using a vector search.
07:50pm - Break
08:00 - Vikram Haridas, Lead Product Manager at Groupon “Implementing AI-Driven Product Innovations: Strategic Insights and Practical Applications”
Vikram Haridas, from Groupon, will reveal how AI can supercharge product roadmaps. Learn how to balance excitement with realism as you scale AI features and discover practical use cases. Get insights into Groupon’s success with AI-powered deal optimisation and automated merchant onboarding, and learn how to implement these strategies in your own business.
08:40 - Shubhangi Goyal, Data Analyst @ ICS.AI Ltd and Nidhi Agrawal Director @UBS, “Generative AI and its use cases”
Our session will explore the transformative potential of Generative AI, focusing on its use cases in matching algorithms and its applications in the financial industry. We’ll dive into how AI models enhance person-matching processes by analysing large datasets for customer service, and personalisation. Additionally, we’ll examine how Generative AI is revolutionising the financial sector.
09:10pm - Wrap up, drinks at Angel London
New Feature in Development: Enhancing Harmony with User-Centred Discovery At Harmony, we’re working on a new feature aimed at making data exploration and analysis even more efficient and intuitive. To ensure this feature addresses real needs, we’re conducting co-design sessions with researchers, data-managers and other users, allowing us to develop a tool that solves real-life user requirements. The Co-Design Approach: Co-design allows us to build this feature with direct input from those who will use it most.
We have a few more issues that have been added to the issue trackers. If you are new and would like to make a pull request in either the Python or R libraries feel free to pick these up - they should be quite small. Easy issues in Python library We would like to expose the “between instrument matches” and the “negation” switches in the Python library and then from the API side.