Sorry, you need to enable JavaScript to visit this website.

Network data can be conveniently modeled as a graph signal, where data values are assigned to the nodes of a graph describing the underlying network topology. Successful learning from network data requires methods that effectively exploit this graph structure. Graph neural networks (GNNs) provide one such method and have exhibited promising performance on a wide range of problems. Understanding why GNNs work is of paramount importance, particularly in applications involving physical networks.

An increasing number of distributed machine learning applications require efficient communication of neural network parameterizations. DeepCABAC, an algorithm in the current working draft of the emerging MPEG-7 part 17 standard for compression of neural networks for multimedia content description and analysis, has demonstrated high compression gains for a variety of neural network models. In this paper we propose a method for employing DeepCABAC in a Federated Learning scenario for the exchange of intermediate differential parameterizations.

Phoneme boundary detection plays an essential first step for a variety of speech processing applications such as speaker diarization, speech science, keyword spotting, etc. In this work, we propose a neural architecture coupled with a parameterized structured loss function to learn segmental representations for the task of phoneme boundary detection. First, we evaluated our model when the spoken phonemes were not given as input.

Building upon advances on optimal transport and anomaly detection, we propose a generalization of an unsupervised and automatic method for detection of significant deviation from reference signals. Unlike most existing approaches for anomaly detection, our method is built on a non-parametric framework exploiting the optimal transportation to estimate deviation from an observed distribution.

We propose a unified compression framework that uses generative adversarial networks (GAN) to compress image and speech signals. The compressed signal is represented by a latent vector fed into a generator network which is trained to produce high-quality signals that minimize a target objective function. To efficiently quantize the compressed signal, non-uniformly quantized optimal latent vectors are identified by iterative back-propagation with ADMM optimization performed for each iteration.

In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem, where the target data are unlabelled and arriving sequentially. The traditional methods on the OUDA problem mainly focus on transforming each arriving target data to the source domain, and they do not sufficiently consider the temporal coherency and accumulative statistics among the arriving target data. We propose a multi-step framework for the OUDA problem, which institutes a novel method to compute the mean-target subspace inspired by the geometrical interpretation on the Euclidean space.

Construction of learning model under computational and energy constraints, particularly in highly limited training time requirement is a critical as well as unique necessity of many practical IoT applications that use time series sensor signal analytics for edge devices. Yet, majority of the state-of-the-art algorithms and solutions attempt to achieve high performance objective (like test accuracy) irrespective of the computational constraints of real-life applications.