3 papers
cs.CV2026
An accuracy-aware extension to LRP-based pruning for CNNs to prevent cascading accuracy degradation in data-scarce transfer learning
Daisuke Yasui, Toshitaka Matsuki, Hiroshi Sato
Convolutional Neural Networks (CNNs) pre-trained on large-scale datasets such as ImageNet are widely used as feature extractors to construct high-accuracy classification models fro…
cs.RO2026
Visualizing Latent Phase Structures in Locomotion Policies: A Multi-Environment Study with Temporal Feature Extension
Daisuke Yasui, Toshitaka Matuki, Hiroshi Sato
Deep reinforcement learning (DRL) has been shown to achieve high performance on locomotion control tasks in MuJoCo benchmarks such as HalfCheetah, Ant, and Walker2D. However, visua…
cs.RO2026
Uncovering Latent Phase Structures and Branching Logic in Locomotion Policies: A Case Study on HalfCheetah
Daisuke Yasui, Toshitaka Matsuki, Hiroshi Sato
In locomotion control tasks, Deep Reinforcement Learning (DRL) has demonstrated high performance; however, the decision-making process of the learned policy remains a black box, ma…