TY - GEN
T1 - A Data Driven Similarity Measure and Example Mapping Function for General , Unlabelled Data Sets
AU - Lejeune, Damien
AU - Driessens, Kurt
PY - 2016
Y1 - 2016
N2 - Deep networks such as autoencoders and deep belief nets are able to construct alternative, and often informative, repre-sentations of unlabeled data by searching for (hidden) structure and correlations between the features chosen to represent the data and combining them into new features that allow sparse representations of the data. These representations have been chosen to often increase the accuracy of further classification or regression accuracy when compared to the original, often human chosen representations. In this work, we attempt an investigation of the relation between such discovered representations found using related but differently repre-sented sets of examples. To this end, we combine the cross-domain comparison capabilities of unsupervised manifold alignment with the unsupervised feature construction of deep belief nets, resulting in an example mapping function that allows re-encoding examples from any source to any target task. Using the t-Distributed Stochastic Neighbour Embedding technique to map translated and real exam-ples to a lower dimensional space, we employ KL-divergence to de-fine a dissimilarity measure between data sets enabling us to measure found representation similarities between domains.
AB - Deep networks such as autoencoders and deep belief nets are able to construct alternative, and often informative, repre-sentations of unlabeled data by searching for (hidden) structure and correlations between the features chosen to represent the data and combining them into new features that allow sparse representations of the data. These representations have been chosen to often increase the accuracy of further classification or regression accuracy when compared to the original, often human chosen representations. In this work, we attempt an investigation of the relation between such discovered representations found using related but differently repre-sented sets of examples. To this end, we combine the cross-domain comparison capabilities of unsupervised manifold alignment with the unsupervised feature construction of deep belief nets, resulting in an example mapping function that allows re-encoding examples from any source to any target task. Using the t-Distributed Stochastic Neighbour Embedding technique to map translated and real exam-ples to a lower dimensional space, we employ KL-divergence to de-fine a dissimilarity measure between data sets enabling us to measure found representation similarities between domains.
U2 - 10.3233/978-1-61499-672-9-158
DO - 10.3233/978-1-61499-672-9-158
M3 - Conference article in proceeding
SN - 9781614996729
T3 - Proceedings of the 22nd European Conference on Artificial Intelligence (ECAI'16)
SP - 158
EP - 166
BT - Proceedings of the 22nd European Conference on Artificial Intelligence (ECAI'16)
ER -