Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Tutorial: Build your first neural network from scratch

9 minute read

Published:

In this episode, we want to investigate a simple working neural network (NN) anatomically, without the use of any deep learning package. You might find it very interesting to design every single element that is essential to perform forward and backward propagation. Every piece of component can be put up together like playing a LEGO game!

LaTeX on Github Pages+minimal mistakes+MathJax

3 minute read

Published:

To have $\LaTeX$ equations on this website, which is run on Github Pages using Jekyll and AcademicPages (a fork of Minimal Mistakes), I had to make a few guesses, so here are the secrets.

music

Travel with Your Ears

Concert, Auditorium, Yuen Long Theatre, 2022

Featured Music: Solveig’s Song / Ich Liebe dich / Blue Danube / In a Persian Market / Mendelssohn Violin Concerto E Minor OP.64 / Elgar cello concerto.

Dans L’interminable Pas De La Danse

Concert, Wesleyan House, Wan Chai, 2023

Featured Mussic: The Cup of Life; Rondeau; Cavalerie Legere; Ombre Legere from Le Pardon de Ploermel; Medidation; Sicilienne; Elegie; Dolly; Les Miserables; L’amour est Bleu; Tout Gouter. For more information, visit here.

HKGNA Concert

Concert, Jockey Club Auditorium, the Hong Kong Polythechnic University, 2023

Featured Music:

  • A. Borodin-Polovetsian Dances from Prince Igor, Act II No. 8 and 17
  • Russo-street music for harmonica and orchestra, 1st and 4th movement
  • J. William Escapades for saxophone and orchestra
  • L. Bernstein Symphonic Dances from Westside Story

portfolio

publications

Online Inference in High-Dimensional Models

Published in to submit, 2023

Online statistical inference refers to an inferential method where, as data sequentially becomes available, it’s employed to update the model’s parameters at every step. This approach has broad applications in fields such as network security, quantitative finance, and recommendation systems, among others. In contrast to offline techniques where the entire dataset is used for training, online learning algorithms are anticipated to offer computational efficiency while still delivering statistical results that are comparable to their offline counterparts.

Recommended citation: Han, R., Luo, L., Luo, Y., Lin, Y., & Huang, J. (2023). Online Inference in High-dimensional Models. To submit.

talks

teaching