Unleashing the Power of Absence and Surprise
Teaching AI the Power of Surprise
Can a machine be surprised?
We explore how artificial intelligence can learn not just from data, but from the unexpected. Our method, Learning via Surprisability (LvS), teaches AI systems to form expectations and adjust when reality diverges, just as humans do.
Watch my short talk — Teaching AI the Power of Surprise
By learning from surprise, AI becomes more efficient, adaptable, and explainable. We’ve applied LvS to social media, political discourse, and biomedical data, revealing how absence and deviation can be as meaningful as presence.
If you’d like to support this research and help advance more human-like, transparent AI learning, visit: Support Learning via Surprisability (LvS)
Enjoy Reading This Article?
Here are some more articles you might like to read next:
- Lab Celebration: Eran's RecSys 2025 Paper!
- Paper Alert: What Travelers Say vs. What They Rate
- Congratulations to Roi Alfassi — Part of His Master's Thesis Highlighted at HAI-GEN, IUI'2025!
- From Feelings to Fingerprints: A Talk at the Department of Communication Colloquium
- Reflections from the NetSciX'25 Keynote
- Interpretable Transformation and Analysis of Timelines through Learning via Surprisability (LvS)
- Harnessing AI for Creative Collaboration: Insights from Our Brainwriting Study
- Beyond R0: Unraveling COVID-19's Transmission Mysteries Through Temporal Network Analysis
- Talk at TAU's Cyber Week, June 26, 2023
- A New Paper in PLoS ONE: Early Estimation of the Prevalence of a Disease