← Search

Kentaro Ohno

2 accepted papers

2023

Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks

AAAI 2023technical

Gate functions in recurrent models, such as an LSTM and GRU, play a central role in learning various time scales in modeling time series data by using a bounded activation function. However, it is difficult to train gates to capture extremely long time scales due to gradient vanishing of the bounded…

2023

One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training

ICML 2023poster

This paper proposes a new loss function for adversarial training. Since adversarial training has difficulties, e.g., necessity of high model capacity, focusing on important data points by weighting cross-entropy loss has attracted much attention. However, they are vulnerable to sophisticated attacks…

Cited by 12SourcePDFScholar