506 citations · 1.2k across the 55 of their papers we have counts for
13 papers · 1 filter
Connecting First and Second Order Recurrent Networks with Deterministic Finite Automata
Qinglong Wang, Kaixuan Zhang, Xue Liu +1
We propose an approach that connects recurrent networks with different orders of hidden interaction with regular grammars of different levels of complexity. We argue that the corre…
Shapley Homology: Topological Analysis of Sample Influence for Neural Networks
Kaixuan Zhang, Qinglong Wang, Xue Liu +1
Data samples collected for training machine learning models are typically assumed to be independent and identically distributed (iid). Recent research has demonstrated that this as…
Verification of Recurrent Neural Networks Through Rule Extraction
Qinglong Wang, Kaixuan Zhang, Xue Liu +1
The verification problem for neural networks is verifying whether a neural network will suffer from adversarial samples, or approximating the maximal allowed scale of adversarial p…
Conducting Credit Assignment by Aligning Local Representations
Alexander G. Ororbia, Ankur Mali, Daniel Kifer +1
Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to…
Active Learning of Strict Partial Orders: A Case Study on Concept Prerequisite Relations
Chen Liang, Jianbo Ye, Han Zhao +2
Strict partial order is a mathematical structure commonly seen in relational data. One obstacle to extracting such type of relations at scale is the lack of large-scale labels for…
A Comparative Study of Rule Extraction for Recurrent Neural Networks
Qinglong Wang, Kaixuan Zhang, Alexander G. Ororbia +3
Understanding recurrent networks through rule extraction has a long history. This has taken on new interests due to the need for interpreting or verifying neural networks. One basi…
Learning to Adapt by Minimizing Discrepancy
Alexander G. Ororbia, Patrick Haffner, David Reitter +1
We explore whether useful temporal neural generative models can be learned from sequential data without back-propagation through time. We investigate the viability of a more neuroc…
An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks
Qinglong Wang, Kaixuan Zhang, Alexander G. Ororbia +3
Rule extraction from black-box models is critical in domains that require model validation before implementation, as can be the case in credit scoring and medical diagnosis. Though…
Learning Adversary-Resistant Deep Neural Networks
Qinglong Wang, Wenbo Guo, Kaixuan Zhang +4
Deep neural networks (DNNs) have proven to be quite effective in a vast array of machine learning tasks, with recent examples in cyber security and autonomous vehicles. Despite the…
Using Non-invertible Data Transformations to Build Adversarial-Robust Neural Networks
Qinglong Wang, Wenbo Guo, Alexander G. Ororbia +6
Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of…
Adversary Resistant Deep Neural Networks with an Application to Malware Detection
Qinglong Wang, Wenbo Guo, Kaixuan Zhang +4
Beyond its highly publicized victories in Go, there have been numerous successful applications of deep learning in information retrieval, computer vision and speech recognition. In…
Unifying Adversarial Training Algorithms with Flexible Deep Data Gradient Regularization
Alexander G. Ororbia, C. Lee Giles, Daniel Kifer
Many previous proposals for adversarial training of deep neural nets have included di- rectly modifying the gradient, training on a mix of original and adversarial examples, using…
Online Semi-Supervised Learning with Deep Hybrid Boltzmann Machines and Denoising Autoencoders
Alexander G. Ororbia, C. Lee Giles, David Reitter
Two novel deep hybrid architectures, the Deep Hybrid Boltzmann Machine and the Deep Hybrid Denoising Auto-encoder, are proposed for handling semi-supervised learning problems. The…