Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Ororbia II, Alexander G."'
We present Column2Vec, a distributed representation of database columns based on column metadata. Our distributed representation has several applications. Using known names for groups of columns (i.e., a table name), we train a model to generate an a
Externí odkaz:
http://arxiv.org/abs/1903.08621
Autor:
Wang, Qinglong, Zhang, Kaixuan, Ororbia II, Alexander G., Xing, Xinyu, Liu, Xue, Giles, C. Lee
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 basic form for representing stateful rules is deterministic finite automat
Externí odkaz:
http://arxiv.org/abs/1801.05420
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 neurocognitively-grounded approach in the context of unsupervised generative
Externí odkaz:
http://arxiv.org/abs/1711.11542
Autor:
Wang, Qinglong, Zhang, Kaixuan, Ororbia II, Alexander G., Xing, Xinyu, Liu, Xue, Giles, C. Lee
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 already a challenging problem in statistical learning in general, the
Externí odkaz:
http://arxiv.org/abs/1709.10380
We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion. Through the use of skip-connections, our model can successfully learn and infer a latent, hiera
Externí odkaz:
http://arxiv.org/abs/1705.05994
Learning useful information across long time lags is a critical and difficult problem for temporal neural models in tasks such as language modeling. Existing architectures that address the issue are often complex and costly to train. The Differential
Externí odkaz:
http://arxiv.org/abs/1703.08864
Autor:
Wang, Qinglong, Guo, Wenbo, Zhang, Kaixuan, Ororbia II, Alexander G., Xing, Xinyu, Liu, Xue, Giles, C. Lee
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 superior performance of DNNs in these applications, it has been recen
Externí odkaz:
http://arxiv.org/abs/1612.01401
Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal la
Externí odkaz:
http://arxiv.org/abs/1612.00377
Autor:
Wang, Qinglong, Guo, Wenbo, Ororbia II, Alexander G., Xing, Xinyu, Lin, Lin, Giles, C. Lee, Liu, Xue, Liu, Peng, Xiong, Gang
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 autonomous vehicles. However, despite their superior performance in m
Externí odkaz:
http://arxiv.org/abs/1610.01934
Autor:
Wang, Qinglong, Guo, Wenbo, Zhang, Kaixuan, Ororbia II, Alexander G., Xing, Xinyu, Giles, C. Lee, Liu, Xue
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 cybersecurity, an increasing number of companies have become excited
Externí odkaz:
http://arxiv.org/abs/1610.01239