CDAE4InfoExtraction
Artificial Intelligence
Computer Vision
NLP
Generative Modeling
A system for the extraction of hierarchical information across multiple, unrelated domains that uses Capsule Networks, statistical-distribution based systems and Variational Autoencoders to extract ’characteristics’ of an image. a characteristic extraction algorithm and the Multi-domain Image Characteristics Dataset of characteristic-tagged images to simulate the way a human brain classifies cross-domain information and generates insight. The intent was to identify prominent characteristics in data and use this identification mechanism to auto-generate insight from data in other unseen domains.
Technologies Used: Python, Tensorflow, Generative Modeling.
My Role:
- Experimented with Capsule Network Training algorithms.
- Optimized the VAE architecture.
- Web scraping to create the Multi-domain Image Characteristics Dataset.