More Like this

1. Dual Policy Distillation

   https://doi.org/10.24963/ijcai.2020/435  

   Lai, Kwei-Herng; Zha, Daochen; Li, Yuening; Hu, Xia (July 2020, Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence)

   Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is computationally expensive. Moreover, the performance of the student model could be limited by the teacher model if the teacher model is not optimal. In the light of collaborative learning, we study the feasibility of involving joint intellectual efforts from diverse perspectives of student models. In this work, we introduce dual policy distillation (DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment and extract knowledge from each other to enhance their learning. The key challenge in developing this dual learning framework is to identify the beneficial knowledge from the peer learner for contemporary learning-based reinforcement learning algorithms, since it is unclear whether the knowledge distilled from an imperfect and noisy peer learner would be helpful. To address the challenge, we theoretically justify that distilling knowledge from a peer learner will lead to policy improvement and propose a disadvantageous distillation strategy based on the theoretical results. The conducted experiments on several continuous control tasks show that the proposed framework achieves superior performance with a learning-based agent and function approximation without the use of expensive teacher models. 

   more » « less
2. Inkjet Printed Flexible Dual-Band Dual-Sense Circularly Polarized Patch Antenna

   https://doi.org/10.1109/ACCESS.2024.3389706  

   Hossain, Abdul Rakib; Sagar, Md_Samiul Islam; Mertvyy, Aleks Aleksandrovich; Sekhar, Praveen Kumar; Karacolak, Tutku (January 2024, IEEE Access)

   This research proposes an inkjet printed dual-band dual-sense circularly polarized antenna using CPW-feeding on PET substrate. The antenna is designed and optimized using ANSYS HFSS, which operates at 4.01 GHz - 5.05 GHz (22.96%) and 6.23 GHz - 7.58 GHz (19.55%) with a return loss of <−10 dB. On top of that, the antenna shows an axial ratio of less than 3 dB at 4.23 GHz - 4.62 GHz (8.81%) and 7.11 GHz - 7.36 GHz (3.45%), whereas left hand circular polarization (LHCP) is observed in the first band and right hand circular polarization (RHCP) is observed in the second band. The overall dimensions of the antenna is x x , where is the free-space wavelength at the lowest circular polarization frequency. Measurement of the fabricated version shows good agreement with the simulated version. To the best of author’s knowledge, this proposed design is the first circularly polarized … 

   more » « less
3. Asynchronous Dual Free Stochastic Dual Coordinate Ascent for Distributed Data Mining

   Huo, Zhouyuan; Jiang, Xue; Huang, Heng (January 2018, IEEE International Conference on Data Mining (ICDM 2018))
4. A Dual-Attention-Based Stock Price Trend Prediction Model With Dual Features

   https://doi.org/10.1109/ACCESS.2019.2946223  

   Chen, Yingxuan; Lin, Weiwei; Wang, James Z. (January 2019, IEEE Access)
5. Dual-Cycle: Self-Supervised Dual-View Fluorescence Microscopy Image Reconstruction using CycleGAN

   https://doi.org/10.1109/ICASSP49357.2023.10095386  

   Kerepecky, Tomas; Liu, Jiaming; Ng, Xue Wen; Piston, David W.; Kamilov, Ulugbek S. (June 2023, Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing)

   Three-dimensional fluorescence microscopy often suffers from anisotropy, where the resolution along the axial direction is lower than that within the lateral imaging plane. We address this issue by presenting Dual-Cycle, a new framework for joint deconvolution and fusion of dual-view fluorescence images. Inspired by the recent Neuroclear method, Dual-Cycle is designed as a cycle-consistent generative network trained in a self-supervised fashion by combining a dual-view generator and prior-guided degradation model. We validate Dual-Cycle on both synthetic and real data showing its state-of-the-art performance without any external training data. 

   more » « less