29 citations · 63 across the 7 of their papers we have counts for
10 papers
Sound Explanation for Trustworthy Machine Learning
Kai Jia, Pasapol Saowakon, Limor Appelbaum +1
We take a formal approach to the explainability problem of machine learning systems. We argue against the practice of interpreting black-box models via attributing scores to input…
Effective Neural Network Regularization With BinMask
Kai Jia, Martin Rinard
regularization of neural networks is a fundamental problem. In addition to regularizing models for better generalizability, regularization also applies to selecting inp…
Mixed Capability Games
Kai Jia, Martin Rinard, Yichen Yang
We present a new class of strategic games, mixed capability games, as a foundation for studying how different player capabilities impact the dynamics and outcomes of strategic game…
On the Impact of Player Capability on Congestion Games
Yichen Yang, Kai Jia, Martin Rinard
We study the impact of player capability on social welfare in congestion games. We introduce a new game, the Distance-bounded Network Congestion game (DNC), as the basis of our stu…
Verifying Low-dimensional Input Neural Networks via Input Quantization
Kai Jia, Martin Rinard
Deep neural networks are an attractive tool for compressing the control policy lookup tables in systems such as the Airborne Collision Avoidance System (ACAS). It is vital to ensur…
SANM: A Symbolic Asymptotic Numerical Solver with Applications in Mesh Deformation
Kai Jia
Solving nonlinear systems is an important problem. Numerical continuation methods efficiently solve certain nonlinear systems. The Asymptotic Numerical Method (ANM) is a powerful c…
Efficient Exact Verification of Binarized Neural Networks
Kai Jia, Martin Rinard
Concerned with the reliability of neural networks, researchers have developed verification techniques to prove their robustness. Most verifiers work with real-valued networks. Unfo…
Exploiting Verified Neural Networks via Floating Point Numerical Error
Kai Jia, Martin Rinard
Researchers have developed neural network verification algorithms motivated by the need to characterize the robustness of deep neural networks. The verifiers aspire to answer wheth…
MegDet: A Large Mini-Batch Object Detector
Chao Peng, Tete Xiao, Zeming Li +5
The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network,…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…