8 papers
Drift-Free Conservative Dynamics from Quantized Interaction Rules
Park Junhu, Youngsoo Ha, Myungjoo Kang
Conservation laws are conventionally discretized through floating-point flux evaluation, with invariants obtained by cancellation of approximate interface contributions and admissi…
Continuum dynamics from quantised interaction rules
Park Junhu, Youngsoo Ha, Myungjoo Kang
Hyperbolic conservation laws are conventionally solved by evolving reconstructed floating-point fields, incurring both computational overhead and structural diffusion near disconti…
Why Rectified Power Unit Networks Fail and How to Improve It: An Effective Field Theory Perspective
Taeyoung Kim, Myungjoo Kang
The Rectified Power Unit (RePU) activation function, a differentiable generalization of the Rectified Linear Unit (ReLU), has shown promise in constructing neural networks due to i…
Divergence-Based Similarity Function for Multi-View Contrastive Learning
Jae Hyoung Jeon, Cheolsu Lim, Myungjoo Kang
Recent success in contrastive learning has sparked growing interest in more effectively leveraging multiple augmented views of data. While prior methods incorporate multiple views…
Residual Connection-Enhanced ConvLSTM for Lithium Dendrite Growth Prediction
Hosung Lee, Byeongoh Hwang, Dasan Kim +1
The growth of lithium dendrites significantly impacts the performance and safety of rechargeable batteries, leading to short circuits and capacity degradation. This study proposes…
Decomposition of one-layer neural networks via the infinite sum of reproducing kernel Banach spaces
Seungcheol Shin, Myungjoo Kang
In this paper, we define the sum of RKBSs using the characterization theorem of RKBSs and show that the sum of RKBSs is compatible with the direct sum of feature spaces. Moreover,…