Deep Autoencoders for Scientific Data Compression
- Mentors
- Alexander Ekman
- Organization
- CERN-HSF
- Technologies
- python, jupyter, spark, pytorch, unix
- Topics
- machine learning, deep learning, Neural networks, data compression
Development and Deployment of a Lossy Compression Tool 'Baler' that uses deep autoencoders to flexibly compress scientific data. Use Baler to compress data for LHC experiments like ATLAS and improve existing Baler model to be more robust and accurate while reconstructing data. Document and Benchmark Baler's performance for real-world physics experiment and explore it's capabilities on non-scientific data.