He (born in 1990) is currently a Research Associate Professor of School of Data and Computer Science, Sun Yat-sen University, Guangzhou. He received B.S. in mathematics and applied mathematics from Zhangzhou Normal University, Zhangzhou in June 2012, and Ph.D. in computational mathematics from Sun Yat-sen University, Guangzhou in June 2017, respectively. From October 2015 to October 2016, he was a Research Assistant with the Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton, Alberta, Canada.
Time-Frequency Analysis and Kernel Methods in Machine Learning
1. R. Lin, H. Zhang and J. Zhang, On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions.
2. R. Lin*, An Optimal Convergence Rate for Gaussian Regularized Shannon Sampling Series, arXiv: 1711.04909.
3. R. Lin and H. Zhang*, Convergence Analysis of the Gaussian Regularized Shannon Sampling Series, Numerical Functional Analysis and Optimization, 38 (2017), no. 2,224–247.
4. F. Huang, R. Lin* and Y.Yang, The Circular Bedrosian Identity and Multidimensional Periodic Analytic Signals, Complex Variables and Elliptic Equations, 62(2017), no. 2, 199–213.
5. R. Lin and H. Zhang*, Existence of the Bedrosian Identity for Fourier Multiplier Operators, Forum Mathematicum, 28 (2016), no. 4, 749–759.
6. W. Hu, R. Lin* and H. Zhang, The Circular Bedrosian Identity for Translation-Invariant Operators: Existence and Characterization, Mathematical Methods in the Applied Sciences, 38 (2015), no.18, 5264–5270.
1. Invited talk, 25 mins. The Second Hangzhou Workshop on Harmonic Analysis and Applications 2017. Hangzhou. December 16-17, 2017. (Topic: Shannon's Sampling Theorem II)
2. Invited talk, 40 mins. TSMIF Sanya workshop: From Approximation Theory to Real World Applications. TSMIF, Sanya. December 11-15, 2017. (Topic: Shannon's Sampling Theorem I)
3. Contributed talk, 20 mins. International Conference on Computational Harmonic Analysis. Fudan University, Shanghai. May 24-28, 2017. (Topic: Reproducing Kernel Banach Spaces)
2017.09-2018.01 计算数学基础之小波分析(Wavelet Analysis). Outline of this course is listed below.
Lecture 1: Introduction to DCT- and DWT-based JPEG
Lecture 2: Regularity of a Function and Decay of its Fourier Coefficients
Lecture 3: DFT, FFT and DCT
Lecture 4: Fourier transform on L1(R) and L2(R)
Lecture 5: Approximation Identity and Shannon's Sampling Theorem
Lecture 6: Celebrated Results in Fourier Analysis
Lecture 7: Wavelet Analysis: Haar Wavelet
Lecture 8: General Multiresolution Analysis and the Mallat Algorithm
Lecture 9: Filter Banks (Symmetry, Vanishing Moments, Sum Rules and Linear-phase Moments)
Lecture 10: Daubechies' Orthogonal Wavelets
Lecture 11: Biorthogonal Wavelets and Discrete Wavelet Transform
Seminar: The Mathematical Foundation for Deep Learning
Every Thusday morning 9:30--11:30 am, March to June, 2018. 地点: 超算五楼509会议室
Lecture 3: Convolution Neural Networks (CNN)
Assignment 1: Training DNN, kNN, SVM, CNN on the Dataset MNIST
Lecture 4: Recurrent Neural Networks (RNN) and LSTM (Speaker: 李悦)
Lecture 5: Wav2Letter for Speech Recognition
Lecture 6: Generative Adversarial Networks (GAN)
Lecture 7: Autoencoders (Speaker: 袁淦钊)
----> Research-based Seminar <----