• Publications
  • Influence
Neighbourhood Components Analysis
TLDR
A novel method for learning a Mahalanobis distance measure to be used in the KNN classification algorithm that directly maximizes a stochastic variant of the leave-one-out KNN score on the training set. Expand
context2vec: Learning Generic Context Embedding with Bidirectional LSTM
TLDR
This work presents a neural model for efficiently learning a generic context embedding function from large corpora, using bidirectional LSTM, and suggests they could be useful in a wide variety of NLP tasks. Expand
Training deep neural-networks using a noise adaptation layer
TLDR
This study presents a neural-network approach that optimizes the same likelihood function as optimized by the EM algorithm but extended to the case where the noisy labels are dependent on the features in addition to the correct labels. Expand
Hierarchical Clustering of a Mixture Model
TLDR
An efficient algorithm for reducing a large mixture of Gaussians into a smaller mixture while still preserving the component structure of the original model is proposed by clustering the components by avoiding the need for explicit resampling of datapoints. Expand
Global Learning of Typed Entailment Rules
TLDR
The results show that using global transitivity information substantially improves performance over this resource and several baselines, and that the scaling methods allow us to increase the scope of global learning of entailment-rule graphs. Expand
An efficient image similarity measure based on approximations of KL-divergence between two gaussian mixtures
TLDR
Two new methods for approximating the Kullback-Liebler (KL) divergence between two mixtures of Gaussians based on matching between the Gaussian elements of the two Gaussian mixture densities are presented. Expand
GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
TLDR
It is shown that generated medical images can be used for synthetic data augmentation, and improve the performance of CNN for medical image classification, and generalize to other medical classification applications and thus support radiologists’ efforts to improve diagnosis. Expand
Precise Detection in Densely Packed Scenes
TLDR
This work proposes a novel, deep-learning based method for precise object detection, designed for such challenging settings as packed retail environments, and shows the method to outperform existing state-of-the-art with substantial margins. Expand
Modeling Word Meaning in Context with Substitute Vectors
TLDR
A variant of substitute vectors is proposed, which is particularly suitable for measuring context similarity and a novel model for representing word meaning in context based on this context representation, which outperforms state-of-the-art results on lexical substitution tasks in an unsupervised setting. Expand
Nonparametric Information Theoretic Clustering Algorithm
TLDR
A novel clustering algorithm based on maximizing the mutual information between data points and clusters is proposed based on utilizing a non-parametric estimation of the average cluster entropies and search for a clustering that maximizes the estimated mutual information. Expand
...
1
2
3
4
5
...