DBTB INT Niyati Parameswaran f
summary
Two lightweight frameworks get described and demonstrated: one for face detection and related generative work, the other for automatic text summarization; both plug into IBM Watson services to measurably improve results on noisy real‑world data. The implementations use neural architectures (autoencoders and recursive variants), training on messy corpora and image sets, and report working prototypes integrated with Watson APIs rather than just theory—examples include end‑to‑end pipeline code, evaluation metrics, and shown improvements in accuracy and summary coherence.
AI-written summary · about
chapters (3)
related talks
22mEmpowering journalism-approaches to automatic text summarization
01h 03mIt's All About AI
17mAI/ML demo derby
58mBits, Bytes and Brains - Where Watson Is and Where its going?
39mBig Data Information Architecture for AI
34mI, Human
01h 00mData, visualization, and designing AI
27mHow to put AI to work in different industries