GithubHelp home page GithubHelp logo

Hi there 👋

I'm an R&D engineer.

From research prospective, I work on how to make current models better with optimized initializers and optimizers, and how to make better models guided by fine-grained evaluation methods, hinted by model attacking experiments.

From engineering prospective, I work on software and hardware to better serve these models with lower cost and higher thoughput, and collaborate with teammates to make use of these products to really serve humankind as much as possible.

黄(Huáng)瓒(Zàn)'s Projects

croaring icon croaring

Roaring bitmaps in C (and C++), with SIMD (AVX2, AVX-512 and NEON) optimizations

dsa.workspace icon dsa.workspace

For Prof. Deng's Data Structure and Algorithms course(MOOC version)

jodie icon jodie

A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"

misc.samples icon misc.samples

Pieces of code extracted from homeworks and mini-projects:tiger:

mlnd.continued icon mlnd.continued

About Udacity's Machine Learning Nanodegree program in Chinese:smiley::rocket:

peak.cu icon peak.cu

Assembler for NVIDIA Volta and Turing GPUs

pmixer icon pmixer

Add README to my profile page by creating the user_id named repo

raft icon raft

RAFT contains fundamental widely-used algorithms and primitives for data science, graph and machine learning.

rnn.embedding icon rnn.embedding

CSE6240 project: RNN->Network Embedding->MOOC Dropout Prediction->:rocket:

rpc.pytorch icon rpc.pytorch

pytorch rpc seems easier to use for distributed training, sample scripts :)

sasrec.pytorch icon sasrec.pytorch

PyTorch(1.6+) implementation of https://github.com/kang205/SASRec

simplenet icon simplenet

From simple artificial neural network for MNIST exercise to Network Analysis :cyclone:

tisasrec.debug icon tisasrec.debug

Based on https://github.com/JiachengLi1995/TiSASRec, replace negative sampling based evaluation with all-item based evaluation and try to make it better for ranking all items.

tracker.eval icon tracker.eval

"REVISITING THE DETAILS WHEN EVALUATING A VISUAL TRACKER":notebook:

wavenet.poc icon wavenet.poc

Show how WaveNet works and how to accelerate model inference in reference to https://github.com/tomlepaine/fast-wavenet

zan.initializer icon zan.initializer

Sample to show how input dim(input_dim for FC layer, for CNN, it's prod(tensor.shape[1:])) reciprocal could be used for initialize NN weights rather than sqrt(input_dim_reciprocal) hinted by Xavier:dragon:

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.