林荣荣

所属研究所、院系: 
数据科学研究所
职称: 
副研究员
E-mail: 
linrr8[at]mail.sysu.edu.cn
办公地点: 
超算中心大楼524室
教师简介: 

July 2017--Present. Research Associate Professor. School of Data and Computer Science, Sun Yat-sen University. Guangzhou, Guangdong, P. R. China.

October 2018-December 2018. Visiting Faculty. Department of Mathematics and Statistics, Old Dominion University. Norfolk, Virginia, USA.

October 2015--October 2016. Research Assistant. Department of Mathematical and Statistical Sciences, University of Alberta. Edmonton, Alberta, Canada.

September 2014--June 2017. Ph.D. in Computational Mathematics. School of Mathematics, Sun Yat-sen University. Guangzhou, Guangdong, P. R. China

研究领域: 

Kernel Methods in Machine Learning [Slides]; Time-Frequency Analysis

Dissertation: The Bedrosian Identity for Fourier Multiplier Operators [Slides]

获奖及荣誉: 

1. Jan 2018-Dec 2020, PI, Fundamental Research Funds for the Central Universities, 120,000 RMB.

代表性论著: 

8. Rongrong Lin, Guohui Song, Haizhang Zhang*, Multi-task Learning in Vector-valued RKBSs with the l1 Norm, 24 Pages.

7. Rongrong Lin, Haizhang Zhang*, Reproducing Kernels with Uniformly Bounded Lebesgue Constants, Under Review, 3 Pages. 

6. Rongrong Lin, Haizhang Zhang*, Jun Zhang, On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions, Under Review, 25 Pages. [Slides]

5. Rongrong Lin*, An Optimal Convergence Rate for Gaussian Regularized Shannon Sampling Series, Numerical Functional Analysis and Optimization, Accepted, 14 Pages. [PDF]

4. Rongrong Lin, Haizhang Zhang*, Convergence Analysis of the Gaussian Regularized Shannon Sampling Series, Numerical Functional Analysis and Optimization, 38 (2017), no. 2,224–247. [PDF]

3. Fukeng Huang, Rongrong Lin*, Yunfei Yang, The Circular Bedrosian Identity and Multidimensional Periodic Analytic Signals, Complex Variables and Elliptic Equations, 62(2017), no. 2, 199–213. [PDF]

2. Rongrong Lin, Haizhang Zhang*, Existence of the Bedrosian Identity for Fourier Multiplier Operators, Forum Mathematicum, 28 (2016), no. 4, 749–759. [PDF]

1. Wei Hu, Rongrong Lin*, Haizhang Zhang, The Circular Bedrosian Identity for Translation-Invariant Operators: Existence and Characterization, Mathematical Methods in the Applied Sciences, 38 (2015), no.18, 5264–5270. [PDF]

学术会议

3. Contributed talk, 20 mins. The 2nd International Conference on Mathematics of Data Science. Old Dominion University, USA. November 3-4, 2018. (Topic: Multi-task Learning in Vector-valued RKBSs with the l1 norm) 

2. Invited talk, 25 mins. The 2nd International Conference on Kernel-based Approximation Methods in Data Analysis. Guangzhou. May 25-27, 2018. (Topic: Constructions of Reproducing Kernel Banach Spaces) [link]

1. 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)

教授课程

2017.09-2018.01 Wavelet Analysis. 

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

Image Denoising: Matlab Code (Comparison between DCT and DWT) and Lena

 

March 8-July 5, 2018.  Mathematical Foundations of Deep Learning

Lecture 1: Deep Neural Networks (DNN) & Python Code 

Lecture 2: Machine Learning Methods (k-NN,Bayes,CART,AdaBoost,SVM) & Tensorflow Code  

Project 1: Gender Identification by Voice (GitHub & Kaggle)

Lecture 3: Convolutional Neural Networks (e.g., AlexNet, GoogLeNet, VGGNet, ResNet)& Code

Assignment 1: Training DNN, SVM, CNN on the Dataset MNIST

Assignment 2: The usage of scikit-learn

Assignment 3:  MNIST (4 Conv+2 FC, 99.24% Accurary, 8 mins) & Keras Code

Lecture 4: Recurrent Neural Networks (RNN) and LSTM

Lecture 5: Applications of RNNs (Precipitation Nowcasting, NLP, ASR) & Code &Word2Vector

Lecture 6: Restricted Boltzmann Machines (RBM)

Lecture 7: Generative Adversarial Networks (GAN)

Lecture 8:  Sparse Coding and Auto-Encoder (Speaker: Ganzhao Yuan) 

Lecture 9: Object Detection (R-CNN, YOLO)

Project 2: Implementation of YOLO v3 (Code) 

Project 3: Automatic Reading of Water Level (Image)& Keras Code&Test Image

Lecture 10: Kernel Methods and Deep Networks I (RBF Network, DKL, VC Dimension)

Lecture 11: Proximal Algorithm and Majorization Minimization Algorithms (MM)

Lecture 12: Kernel Methods and Deep Networks II (CKN,  Overparametrization)

Project 4: Keyword Spotting (GitHub 1, GitHub 2, Paper)

Lecture 13: Mathematical Foundations of Deep Learning (Approximation Properties)