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

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.

Categories:
28 Views

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.

Categories:
20 Views

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.

Categories:
33 Views

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.

Categories:
12 Views

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.

Categories:
11 Views

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.

Categories:
19 Views

This paper studies the security issue of a gossip-based distributed projected gradient (DPG) algorithm, when it is applied for solving a decentralized multi-agent optimization. It is known that the gossip-based DPG algorithm is vulnerable to insider attacks because each agent locally estimates its (sub)gradient without any supervision. This work leverages the convolutional neural network (CNN) to perform the detection and localization of the insider attackers.

Categories:
10 Views

Finite Rate of Innovation (FRI) theory considers sampling and reconstruction of classes of non-bandlimited continuous signals that have a small number of free parameters, such as a stream of Diracs. The task of reconstructing FRI signals from discrete samples is often transformed into a spectral estimation problem and solved using Prony's method and matrix pencil method which involve estimating signal subspaces. They achieve an optimal performance given by the Cramér-Rao bound yet break down at a certain peak signal-to-noise ratio (PSNR).

Categories:
7 Views

This paper addresses the learning task of estimating driver drowsiness from the signals of car acceleration sensors. Since even drivers themselves cannot perceive their own drowsiness in a timely manner unless they use burdensome invasive sensors, obtaining labeled training data for each timestamp is not a realistic goal. To deal with this difficulty, we formulate the task as a weakly supervised learning. We only need to add labels for each complete trip, not for every timestamp independently.

Categories:
8 Views

Pages