Will Xie

San Francisco, California, United States Contact Info
444 followers 420 connections

Join to view profile

About

willxie.com

Activity

Join now to see all activity

Experience & Education

  • Cosign AI

View Will’s full experience

See their title, tenure and more.

or

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

Publications

Courses

  • ADVANCE ALGORITHMS

    COMP 482

  • AUTONOMOUS ROBOTICS

    CS 393R

  • COMPUTER NETWORKS

    COMP 429

  • COMPUTER SYSTEMS ARCHITECTURE

    ELEC 425

  • GRAPHICAL MODELS

    CS 395T

  • MACHINE LEARNING

    CS 391L

  • NATURAL LANGUAGE PROCESSI

    CS 388

  • OPERATING SYSTEMS

    COMP 421

  • PARALLEL PROGRAMMING

    COMP 323

  • VISUAL RECOGNITION

    CS 381V

  • WIRELESS NETWORKING

    CS 386W

Projects

  • ARCane

    -

    Co-founded and developed a wearable navigational aid for the visually impaired. In an interdisciplinary team of 6 engineers, we created a novel system that uses stereovision to capture depth information from the environment and then wirelessly transfer the data for haptics feedback.

  • Language Grounding

    -

    Researched a novel way to use real world objects and natural language descriptions to associate visual attributes and words to their corresponding concepts in logical form. Through the process, we also created a dataset of 52 objects with 468 descriptions.

  • Predicting Atari game frames

    -

    Researched the action-conditional video prediction problem in the Atari domain by combining Siamese convolutional-deconvolutional neural networks and motion-equivariance regularizer. We designed 3 different neural networks with unique loss functions and tested them on multiple Atari games played by different types autonomous agents. Data was collected with varied frame rates and action sample rates. We evaluated our approaches against the no-action baseline and a neural network only approach…

    Researched the action-conditional video prediction problem in the Atari domain by combining Siamese convolutional-deconvolutional neural networks and motion-equivariance regularizer. We designed 3 different neural networks with unique loss functions and tested them on multiple Atari games played by different types autonomous agents. Data was collected with varied frame rates and action sample rates. We evaluated our approaches against the no-action baseline and a neural network only approach for all the games.

Honors & Awards

  • Rice ECE Affiliates Best Senior Design Project 2nd place winner

    -

  • IEEE Region 5 Circuit Design Competition 1st place winner

    -

  • Rice Entrepreneurship Summit 1st place winner

    -

Languages

  • English

    Native or bilingual proficiency

  • Mandarin Chinese

    Native or bilingual proficiency

  • Cantonese Chinese

    Native or bilingual proficiency

More activity by Will

View Will’s full profile

  • See who you know in common
  • Get introduced
  • Contact Will directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Will Xie in United States

43 others named Will Xie in United States are on LinkedIn

See others named Will Xie

Add new skills with these courses

See all courses