Related papers: Modeling Based on Elman Wavelet Neural Network for…

Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we leverage the intrinsic…

Subjective evaluation results for two low-latency deep neural networks (DNN) are compared to a matured version of a traditional Wiener-filter based noise suppressor. The target use-case is real-world single-channel speech enhancement…

The increasing adoption of Deep Neural Network (DNN)-based Digital Pre-distortion (DPD) in modern communication systems necessitates efficient hardware implementations. This paper presents DPD-NeuralEngine, an ultra-fast, tiny-area, and…

Edge devices demand low energy consumption, cost and small form factor. To efficiently deploy convolutional neural network (CNN) models on edge device, energy-aware model compression becomes extremely important. However, existing work did…

In optical communication systems, short blocklength probabilistic enumerative sphere shaping (ESS) provides both linear shaping gain and nonlinear tolerance. In this work, we investigate the performance and complexity of ESS in comparison…

Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architectures difficult. Recent contributions to deep learning…

Training deep neural networks (DNNs) directly on edge devices has attracted increasing attention, as it offers promising solutions to challenges such as domain adaptation and privacy preservation. However, conventional DNN training…

We study the problem of optimal power allocation in a single-hop ad hoc wireless network. In solving this problem, we propose a hybrid neural architecture inspired by the algorithmic unfolding of the iterative weighted minimum mean squared…

Edge nodes are crucial for detection against multitudes of cyber attacks on Internet-of-Things endpoints and is set to become part of a multi-billion industry. The resource constraints in this novel network infrastructure tier constricts…

This work focuses on online dereverberation for hearing devices using the weighted prediction error (WPE) algorithm. WPE filtering requires an estimate of the target speech power spectral density (PSD). Recently deep neural networks (DNNs)…

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…

In TDD massive MIMO systems, channel estimation under sparse frequency-hopping pilots is challenging: each snapshot captures only one narrow pilot block that hops across frequency, with tens of milliseconds between adjacent snapshots.…

In this work, we investigate the feasibility and effectiveness of employing deep learning algorithms for automatic recognition of the modulation type of received wireless communication signals from subsampled data. Recent work considered a…

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Deep Learning has a hierarchical network architecture to represent the complicated feature of input patterns. We have developed the adaptive structure learning method of Deep Belief Network (DBN) that can discover an optimal number of…

This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…

Power consumption is a major obstacle in the deployment of deep neural networks (DNNs) on end devices. Existing approaches for reducing power consumption rely on quite general principles, including avoidance of multiplication operations and…

The prediction accuracy of the deep neural networks (DNNs) after deployment at the edge can suffer with time due to shifts in the distribution of the new data. To improve robustness of DNNs, they must be able to update themselves to enhance…

Deep neural networks (DNNs) deliver state-of-the-art accuracy on regression and classification tasks, yet two structural deficits persistently obstruct their deployment in safety-critical, resource-constrained settings: (i) opacity of the…

A low-energy hardware implementation of deep belief network (DBN) architecture is developed using near-zero energy barrier probabilistic spin logic devices (p-bits), which are modeled to realize an intrinsic sigmoidal activation function. A…