5 papers
Towards the Mitigation of Confirmation Bias in Semi-supervised Learning: a Debiased Training Perspective
Yu Wang, Yuxuan Yin, Peng Li
Semi-supervised learning (SSL) commonly exhibits confirmation bias, where models disproportionately favor certain classes, leading to errors in predicted pseudo labels that accumul…
Semi-Supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach
Yu Wang, Yuxuan Yin, Karthik Somayaji Nanjangud Suryanarayana +5
Modeling dynamical systems is crucial for a wide range of tasks, but it remains challenging due to complex nonlinear dynamics, limited observations, or lack of prior knowledge. Rec…
Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory
Karthik Somayaji NS, Yu Wang, Malachi Schram +4
Risk-sensitive reinforcement learning (RL) has garnered significant attention in recent years due to the growing interest in deploying RL agents in real-world scenarios. A critical…
A Computational Framework of Cortical Microcircuits Approximates Sign-concordant Random Backpropagation
Yukun Yang, Peng Li
Several recent studies attempt to address the biological implausibility of the well-known backpropagation (BP) method. While promising methods such as feedback alignment, direct fe…
Signal and Image Reconstruction with Tight Frames via Unconstrained -Analysis Minimizations
Peng Li, Huanmin Ge, Pengbo Geng
In the paper, we introduce an unconstrained analysis model based on the minimization for the signal and image reconstruction. We develop some new…