Jinsoo Yoo — accepted AI-conference papers

2024

Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning

Jinsoo Yoo, Yunpeng Liu, Frank Wood, Geoff Pleiss

ICML 2024poster

In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on past data. Our work demonstrates a limitation of this approac…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2022

BayesPCN: A Continually Learnable Predictive Coding Associative Memory

Jinsoo Yoo, Frank Wood

NeurIPS 2022accept

Associative memory plays an important role in human intelligence and its mechanisms have been linked to attention in machine learning. While the machine learning community's interest in associative memories has recently been rekindled, most work has focused on memory recall ($read$) over memory lear…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗