Large Associative Memory Problem Presentation at joint journal club with Baylor College of Medicine.
Hindsight Credit Assignment Presentation at Princeton NLP group journal club.
Multi-Objective Reinforcement Learning Open Talk for General Exam at Computer Science Department, Princeton University.
Global Convergence of Gradient-Based Learning in Zero-Sum Games Presentation in Princeton NLP group meeting.
A Generalized Algorithm for Multi-Objective RL and Policy Adaptation Poster presentation at 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019).
Bridging the Duality Gap between Neural Networks with Hebbian/Anti-Hebbian Plasticity and the Correlation Game Principle Invited presentation at 2019 Asilomar Conference (Neuroscience-Inspired ML Session).
Weight Agnositc Neural Networks Presentation at Princeton NLP group journal club.
Thoughts on Theory of Mind Presentation at Princeton NLP group journal club.
Thoughts on the Emergence of Language Presentation at Princeton NLP group journal club.
Topic Modeling with Hebbian and anti-Hebbian Learning Presentation at Princeton NLP group journal club.
Generalized Algorithms for Multi-Objective Reinforcement Learning with Policy Adaptation Poster presentation at Princeton AIML retreat 2018.
Mitochondrial Size Gradients in Cortical Neurons Suggested by 3D Electron Microscopy Poster presentation at Princeton AIML retreat 2018.
Deep Multi-Objective Reinforcement Learning Student session talk on the 9th ACM-class Student Academic Festival (ASAF 2018) & the 2018 INS-ZY Student Conference.
Affordable On-line Dialogue Policy Learning Presentation at the 2018 SJTU Speech Lab Annual Academic Meeting.
Monitoring Eelgrass Wasting Disease Using Deep Learning & Crowd Wisdom Poster presentation at the 2017 CompSustNet NSF Site Visit.
Companion Teaching:Towards Affordable On-line Dialogue Policy Learning Student session talk on the 8th ACM-class Student Academic Festival (ASAF 2017).
Ideas sparked by Game Theory & Deep Learning “Expert student talk” on Game Theory course.
On-line Dialogue Policy Learning with Companion Teaching Poster presentation at the 15th European Chapter of the Association for Computational Linguistics Conference (EACL 2017).
Value Iteration Network A 7-minute presentation in reading club of Deep Learning course.
Inverse Reinforcement Learning Presentation in CS professional seminar.
A Local Search Heuristic for Facility Location Problems Presentation on Approximation Algorithm course.
Automata Theory A tutorial in discussion class of Introduction to Computer Science course.