Scholars@Duke

• Background
• 

  Education, Training, & Certifications

  • Ph.D., National University of Singapore (Singapore) 2021
• Publications & Artistic Works
• 

  Selected Publications

  • Academic Articles

    • Shen, Z., H. Yang, and S. Zhang. “Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons.” Journal of Machine Learning Research 23 (September 1, 2022).
    • Shen, Z., H. Yang, and S. Zhang. “Optimal approximation rate of ReLU networks in terms of width and depth.” Journal Des Mathematiques Pures Et Appliquees 157 (January 1, 2022): 101–35. https://doi.org/10.1016/j.matpur.2021.07.009.
       Full Text
    • Shen, Zuowei, Haizhao Yang, and Shijun Zhang. “Neural network approximation: Three hidden layers are enough.” Neural Networks : The Official Journal of the International Neural Network Society 141 (September 2021): 160–73. https://doi.org/10.1016/j.neunet.2021.04.011.
       Full Text
    • Shen, Zuowei, Haizhao Yang, and Shijun Zhang. “Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth.” Neural Computation 33, no. 4 (March 2021): 1005–36. https://doi.org/10.1162/neco_a_01364.
       Full Text
    • Lu, J., Z. Shen, H. Yang, and S. Zhang. “DEEP NETWORK APPROXIMATION FOR SMOOTH FUNCTIONS.” Siam Journal on Mathematical Analysis 53, no. 5 (January 1, 2021): 5465–5506. https://doi.org/10.1137/20M134695X.
       Full Text
    • Shen, Z., H. Yang, and S. Zhang. “Deep network approximation characterized by number of neurons.” Communications in Computational Physics 28, no. 5 (November 1, 2020): 1768–1811. https://doi.org/10.4208/CICP.OA-2020-0149.
       Full Text
    • Shen, Zuowei, Haizhao Yang, and Shijun Zhang. “Nonlinear approximation via compositions.” Neural Networks : The Official Journal of the International Neural Network Society 119 (November 2019): 74–84. https://doi.org/10.1016/j.neunet.2019.07.011.
       Full Text

Some information on this profile has been compiled automatically from Duke databases and external sources. (Our About page explains how this works.) If you see a problem with the information, please write to Scholars@Duke and let us know. We will reply promptly.