We derive an optimization method that is based on a closed form solution for the optimal weight scaling in each bin of a discretized value of the prediction confidence.
The experts estimate a mask from the noisy input and the final mask is then obtained as a weighted average of the experts' estimates, with the weights determined by the gating DNN.
In this study we present a deep neural network-based online multi-speaker localisation algorithm based on a multi-microphone array.
In this study we propose a deep clustering algorithm that utilizes variational auto encoder (VAE) framework with a multi encoder-decoder neural architecture.
Error correction codes are an integral part of communication applications and boost the reliability of transmission.
The pressing need to reduce the capacity of deep neural networks has stimulated the development of network dilution methods and their analysis.
We propose a natural extension of the PA algorithm that uses multiple orthogonal translation matrices to model the mapping and derive an algorithm to learn these multiple matrices.
Contextualized word representations, such as ELMo and BERT, were shown to perform well on various semantic and syntactic tasks.
Aligning sentences in a reference summary with their counterparts in source documents was shown as a useful auxiliary summarization task, notably for generating training data for salience detection.
Error correction codes are an integral part of communication applications, boosting the reliability of transmission.
We show that the time consuming local annotations involved in supervised learning can be addressed by a weakly supervised method that can leverage a subset of locally annotated data.
The high cost of generating expert annotations, poses a strong limitation for supervised machine learning methods in medical imaging.
We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings.
Ranked #2 on Dense Object Detection on SKU-110K
The algorithm jointly learns the noise level in the lexicon, finds the set of noisy pairs, and learns the mapping between the spaces.
Detection and segmentation of MS lesions is a complex task largely due to the extreme unbalanced data, with very small number of lesion pixels that can be used for training.
We present a decision concept which explicitly takes into account the input multi-view structure, where for each case there is a different subset of relevant views.
Then we present a novel scheme for liver lesion classification using CNN.
In this paper, we present a data augmentation method that generates synthetic medical images using Generative Adversarial Networks (GANs).
In this work we propose a method for anatomical data augmentation that is based on using slices of computed tomography (CT) examinations that are adjacent to labeled slices as another resource of labeled data for training the network.
Automatic detection of liver lesions in CT images poses a great challenge for researchers.
Specifically, we show that with minor modifications to word2vec's algorithm, we get principled language models that are closely related to the well-established Noise Contrastive Estimation (NCE) based language models.
In this paper we define a measure of dependency between two random variables, based on the Jensen-Shannon (JS) divergence between their joint distribution and the product of their marginal distributions.
This paper presents a novel deep learning architecture to classify structured objects in datasets with a large number of visually similar categories.
We then freeze the parameters of the trained network and use several different datasets to train an adaptation layer that makes the obtained network universal in the sense that it works well for a variety of speakers and speech domains with very different characteristics.
The obtained language modeling is closely related to NCE language models but is based on a simplified objective function.
In this study we address the problem of training a neuralnetwork for language identification using both labeled and unlabeled speech samples in the form of i-vectors.
In this paper we introduce the MeanNN approach for estimation of main information theoretic measures such as differential entropy, mutual information and divergence.