Search Results for author: Michael Sun

Found 5 papers, 3 papers with code

Improving Representational Continuity via Continued Pretraining

1 code implementation26 Feb 2023 Michael Sun, Ananya Kumar, Divyam Madaan, Percy Liang

We consider the continual representation learning setting: sequentially pretrain a model $M'$ on tasks $T_1, \ldots, T_T$, and then adapt $M'$ on a small amount of data from each task $T_i$ to check if it has forgotten information from old tasks.

Continual Learning Representation Learning +1

Do Neural Networks Generalize from Self-Averaging Sub-classifiers in the Same Way As Adaptive Boosting?

no code implementations14 Feb 2023 Michael Sun, Peter Chatain

In recent years, neural networks (NNs) have made giant leaps in a wide variety of domains.

Investigating Effect of Dialogue History in Multilingual Task Oriented Dialogue Systems

no code implementations23 Dec 2021 Michael Sun, Kaili Huang, Mehrad Moradshahi

Therefore, we devise an efficient and effective training solution for multilingual task-orientated dialogue systems, using the same dataset generation pipeline and end-to-end dialogue system architecture as BiToD[5], which adopted some key design choices for a minimalistic natural language design where formal dialogue states are used in place of natural language inputs.

Dialogue State Tracking Task-Oriented Dialogue Systems

Alpha-Mini: Minichess Agent with Deep Reinforcement Learning

1 code implementation22 Dec 2021 Michael Sun, Robert Tan

We train an agent to compete in the game of Gardner minichess, a downsized variation of chess played on a 5x5 board.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.