-
Attendees
- Members of PyDelhi
- PhD and MSc students from JNU
-
Discussion around on-going work:
- Gene Expression - Ajay Verma (from JNU) presented his work on dimensionality reduction of data with use of auto-encoders.
- Vishwas (from JNU) talked about the Burrows–Wheeler Transform algorithm he is implementing to achieve lossless compression of DNA Data (in general sequential data in the biological domain).
- Identifying biomarkers for predicting cancer or other genetic diseases - The speaker was not present.
-
Discussion around domains for which data can be provided by JNU:
- Publicly available DNA data.
- Publicly available astronomical data.
- Census data - The version in JNU has far more information than the one available publically.
- Publicly available financial data
- Environmental data
-
Resources that can be provided by JNU:
- Compute - Clusters with > 1 Tb of RAM
- Storage - Clusters with > 128 Tb of Disk Space
-
Possible Ideas:
- Investing Psychology - Why do people invest in certain companies and not in other companies.
- Identifying traits for savants.
- Sentiment Analysis of Markets using Social Data
- Predicting evolution of languages on a global scale.
-
Future Agenda
- Organise another meet next month, with more members.
- Come up with possible use cases for collaboration.