Share to FacebookShare to TwitterShare by Email
URI: http://hdl.handle.net/2144/1240

Recently Added

  • Learning to scale multilingual representations for vision-language tasks 

    Burns, Andrea; Kim, Donghyun; Wijaya, Derry; Saenko, Kate; Plummer, Bryan A. (2020)
    Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable ...
  • Application of seq2seq models on code correction 

    Huang, Shan; Zhou, Xiao; Chin, Sang (2021)
    We apply various seq2seq models on programming language correction tasks on Juliet Test Suite for C/C++ and Java of Software Assurance Reference Datasets and achieve 75% (for C/C++) and 56% (for Java) repair rates on these ...
  • Reinforcement learning in FlipIt 

    Chin, Sang; Greige, Laura (2020)
    Reinforcement learning has shown much success in games such as chess, backgammon and Go. However, in most of these games, agents have full knowledge of the environment at all times. In this paper, we describe a deep learning ...
  • Application of seq2seq models on code correction 

    Chin, Sang; Huang, Shan; Zhou, Xiao (2020)
    We apply various seq2seq models on programming language correction tasks on Juliet Test Suite for C/C++ and Java of Software Assurance Reference Datasets (SARD), and achieve 75%(for C/C++) and 56%(for Java) repair rates ...
  • A study of pyramid structure for code correction 

    Chin, Sang (2021)
    We demonstrate the implementations of pyramid encoders in both multi-layer GRU and Transformer for seq2seq tasks. We apply the models to the code correction task on Juliet Test Suite for C/C++ and Java of Software Assurance ...
  • GymFG: a framework with a gym interface for FlightGear 

    Chin, Sang; Wood, Andrew; Sidney, Ali; Tarpa, Bishal; Ross, Ryan (2020)
    Over the past decades, progress in deployable autonomous flight systems has slowly stagnated. This is reflected in today's production air-crafts, where pilots only enable simple physics-based systems such as autopilot for ...
  • NodeDrop: a method for finding sufficient network architecture size 

    Jensen, Louis; Harer, Jacob; Chin, Sang (IEEE, 2020-07)
    Determining an appropriate number of features for each layer in a neural network is an important and difficult task. This task is especially important in applications on systems with limited memory or processing power. ...
  • Block switching: a stochastic approach for deep learning security 

    Chin, Sang (2020)
    Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary ...
  • AdvMS: a multi-source multi-cost defense against adversarial attacks 

    Wang, Xiao; Wang, Siyue; Chen, Pin-Yu; Lin, Xue; Chin, Peter (IEEE, 2020-05)
    Designing effective defense against adversarial attacks is a crucial topic as deep neural networks have been proliferated rapidly in many security-critical domains such as malware detection and self-driving cars. Conventional ...
  • Dreaming with ARC 

    Chin, Sang; Banburski, Andrzej; Poggio, Tomaso; Ghandi, Anshula; Alford, Simon; Dandekar, Sylee (2020-12-12)
    Current machine learning algorithms are highly specialized to whatever it is they are meant to do –– e.g. playing chess, picking up objects, or object recognition. How can we extend this to a system that could solve a ...

View more