Related papers: CNN-based Robust Sound Source Localization with SR…
We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost…
Image enhancement is a critical task in computer vision and photography that is often entangled with noise. This renders the traditional Image Signal Processing (ISP) ineffective compared to the advances in deep learning. However, the…
Recent works have demonstrated the viability of utilizing over-fitted implicit neural representations (INRs) as alternatives to autoencoder-based models for neural video compression. Among these INR-based video codecs, Neural Video…
In recent years tremendous efforts have been done to advance the state of the art for Natural Language Processing (NLP) and audio recognition. However, these efforts often translated in increased power consumption and memory requirements…
Sensor nodes in a wireless sensor network (WSN) for security surveillance applications should preferably be small, energy-efficient, and inexpensive with in-sensor computational abilities. An appropriate data processing scheme in the sensor…
Speech-based machine learning systems are sensitive to noise, complicating reliable deployment in emotion recognition and voice pathology detection. We evaluate the robustness of a hybrid quantum machine learning model, quanvolutional…
Building a small-sized fast surveillance system model to fit on limited resource devices is a challenging, yet an important task. Convolutional Neural Networks (CNNs) have replaced traditional feature extraction and machine learning models…
The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…
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…
Neuromorphic computing and, in particular, spiking neural networks (SNNs) have become an attractive alternative to deep neural networks for a broad range of signal processing applications, processing static and/or temporal inputs from…
For time-critical IoT applications using deep learning, inference acceleration through distributed computing is a promising approach to meet a stringent deadline. In this paper, we implement a working prototype of a new distributed…
The rapid advancement of deep learning in medical image analysis has greatly enhanced the accuracy of skin cancer classification. However, current state-of-the-art models, especially those based on transfer learning like ResNet50, come with…
The choice of an optimal time-frequency resolution is usually a difficult but important step in tasks involving speech signal classification, e.g., speech anti-spoofing. The variations of the performance with different choices of…
Accurate localization of organ boundaries is critical in medical imaging for segmentation, registration, surgical planning, and radiotherapy. While deep convolutional networks (ConvNets) have advanced general-purpose edge detection to…
Current CNN-based super-resolution (SR) methods process all locations equally with computational resources being uniformly assigned in space. However, since missing details in low-resolution (LR) images mainly exist in regions of edges and…
We consider a mesh network at the edge of a wireless network that connects users to the core network via multiple base stations. For this scenario, we present a novel tree-search-based algorithm that strives to identify effective…
The recent advent of `Internet of Things' (IOT) has increased the demand for enabling AI-based edge computing. This has necessitated the search for efficient implementations of neural networks in terms of both computations and storage.…
Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale models, leaving the…
Brain-inspired Spiking Neural Networks (SNNs) leverage sparse spikes to encode information and operate in an asynchronous event-driven manner, offering a highly energy-efficient paradigm for machine intelligence. However, the current SNN…
Conventional super-resolution (SR) schemes make heavy use of convolutional neural networks (CNNs), which involve intensive multiply-accumulate (MAC) operations, and require specialized hardware such as graphics processing units. This…