☝ My name is Jialin Lu 陸家林. I also go with the name Lucy, which has been with me for years.
Currently I work at Huawei Vancouver research center.
I am interested in Bezier curves and program synthesis.
I can be reached at luxxxlucy@gmail.com or jialin_lu@sfu.ca
☜ Hover on the picture.
MSc Computing Science, Simon Fraser University
with
Martin Ester
BEng Computer Science, Zhejiang University
BEng Industrial Design, Zhejiang University
CV
Mastodon
More about me
I was born in Lanxi (蘭谿, 'the orchid creek'), a typical southern Yangtze river town. My father practices the art of traditional Chinese calligraphy, specializing in Wei dynasty inscriptions, and is also a provincially recognized calligraphy mentor. I received intensive training from him when I was younger, until I achieved some local/provincial/national awards and participated in exhibitions, after which I ceased training for various reasons. I specialize in the works of Zhao Mengfu (趙孟頫) and Chu Suiliang (褚遂良), in particular 妙嚴寺記 and 陰符經.
The degree in design was, with sincere gratitude, obtained through the International Design Institute of Zhejiang University and the Studio of Design and Innovation program. My master's thesis (with Martin Ester) focused on building interpretable models by infusing deep learning with the crispness of logic, which is related to the general theme of neuro-symbolic integration.
I was into neural-symbolic computation during my master's study, working on networks that produce symbolic predicates for symbolic computation to operate on. This line of work has been inspiring yet has not been very fruitful; the bitter lesson is brutal. I have had a change of mind since then. Probably we should think more about application and less about the methods. Whatever works must have a reason.
Blogs
A Slightly Obsolete Attempt
Deep Generative Model for Chinese Fonts
Papers
Interpretable drug response prediction using a knowledge-based neural network
Oliver Snow, Hossein Sharifi Noghabi, Jialin Lu, Olga Zolotareva, Mark Lee, Martin Ester
KDD 2021
Neural Disjunctive Normal Form
Jialin Lu
Link
2021 Spring. Master thesis
Revisit Recurrent Attention Model from an Active Sampling Perspective
Jialin Lu
Paper
NeurIPS 2019 Neuro↔AI Workshop
An Active Approach for Model Interpretation
Jialin Lu, Martin Ester
Paper
NeurIPS 2019 workshop on Human-centric machine learning (HCML2019)
Checking Functional Modularity in DNN By Biclustering Task-specific Hidden Neurons
Jialin Lu, Martin Ester
Paper
NeurIPS 2019 Neuro↔AI Workshop
Misc
Mirror-Integration and Functional-Regularisation for better control of Deep Nets slide
Oct 14, 2020 at Simon Fraser University
On more interesting blocks with discrete parameters in deep learning
tutorial presentation,
slide
July 8, 2020 at Simon Fraser University
A oursider's survey on Bayesian Deep Learning
during lab meeting,
slide
handout
link
Feb 26, 2020 at Simon Fraser University
Patterns of Shang-dynasty Ritual Bronze Vessels (in Chinese)
Invited talk (In Chinese) for a group of special interests,
Video
Apr 2, 2018 at Zhejiang University
Past Projects
Interpretable Classification by Vertical Neuro-symbolic Integration
Paused research projects
Misc Things
A old introduction of my research can be found here
甚矣!汝之不惠!