activity
20172026
most citedThe Topology and Geometry of Neural Representations

15 citations · 79 across the 26 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.LG2020

Online Semi-Supervised Learning in Contextual Bandits with Episodic Reward

Baihan Lin

We considered a novel practical problem of online learning with episodically revealed rewards, motivated by several real-world applications, where the contexts are nonstationary ov…

cs.LG2020

Predicting human decision making in psychological tasks with recurrent neural networks

Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi

Unlike traditional time series, the action sequences of human decision making usually involve many cognitive processes such as beliefs, desires, intentions, and theory of mind, i.e…

cs.GT2020

Online Learning in Iterated Prisoner's Dilemma to Mimic Human Behavior

Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi

As an important psychological and social experiment, the Iterated Prisoner's Dilemma (IPD) treats the choice to cooperate or defect as an atomic action. We propose to study the beh…

cs.LG2020

Speaker Diarization as a Fully Online Learning Problem in MiniVox

Baihan Lin, Xinxin Zhang

We proposed a novel machine learning framework to conduct real-time multi-speaker diarization and recognition without prior registration and pretraining in a fully online learning…

cs.AI2020

Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL

Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf +2

Artificial behavioral agents are often evaluated based on their consistent behaviors and performance to take sequential actions in an environment to maximize some notion of cumulat…

cs.HC2020

Keep It Real: a Window to Real Reality in Virtual Reality

Baihan Lin

This paper proposed a new interaction paradigm in the virtual reality (VR) environments, which consists of a virtual mirror or window projected onto a virtual surface, representing…