70 citations · 88 across the 7 of their papers we have counts for
7 papers
TexRel: a Green Family of Datasets for Emergent Communications on Relations
Hugh Perkins
We propose a new dataset TexRel as a playground for the study of emergent communications, in particular for relations. By comparison with other relations datasets, TexRel provides…
Neural networks can understand compositional functions that humans do not, in the context of emergent communication
Hugh Perkins
We show that it is possible to craft transformations that, applied to compositional grammars, result in grammars that neural networks can learn easily, but humans do not. This coul…
Compositionality Through Language Transmission, using Artificial Neural Networks
Hugh Perkins
We propose an architecture and process for using the Iterated Learning Model ("ILM") for artificial neural networks. We show that ILM does not lead to the same clear compositionali…
Dialog Intent Induction with Deep Multi-View Clustering
Hugh Perkins, Yi Yang
We introduce the dialog intent induction task and present a novel deep multi-view clustering approach to tackle the problem. Dialog intent induction aims at discovering user intent…
cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCL
Hugh Perkins
This paper presents cltorch, a hardware-agnostic backend for the Torch neural network framework. cltorch enables training of deep neural networks on GPUs from diverse hardware vend…
Fast Parallel SVM using Data Augmentation
Hugh Perkins, Minjie Xu, Jun Zhu +1
As one of the most popular classifiers, linear SVMs still have challenges in dealing with very large-scale problems, even though linear or sub-linear algorithms have been developed…
Gibbs Max-margin Topic Models with Data Augmentation
Jun Zhu, Ning Chen, Hugh Perkins +1
Max-margin learning is a powerful approach to building classifiers and structured output predictors. Recent work on max-margin supervised topic models has successfully integrated i…