Related papers: Hybrid Real- And Complex-Valued Neural Network Con…
Nowadays, due to advanced digital imaging technologies and internet accessibility to the public, the number of generated digital images has increased dramatically. Thus, the need for automatic image enhancement techniques is quite apparent.…
Neural network acoustic models have significantly advanced state of the art speech recognition over the past few years. However, they are usually computationally expensive due to the large number of matrix-vector multiplications and…
Quantum neural networks represent a new machine learning paradigm that has recently attracted much attention due to its potential promise. Under certain conditions, these models approximate the distribution of their dataset with a truncated…
When designing fully-convolutional neural network, there is a trade-off between receptive field size, number of parameters and spatial resolution of features in deeper layers of the network. In this work we present a novel network design…
One of the main challenges in drug discovery is to find molecules that bind specifically and strongly to their target protein while having minimal binding to other proteins. By predicting binding affinity, it is possible to identify the…
I/Q modulation classification is a unique pattern recognition problem as the data for each class varies in quality, quantified by signal to noise ratio (SNR), and has structure in the complex-plane. Previous work shows treating these…
This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimensional convolutions computed alongside the time domain,…
There are several numerical models that describe real phenomena being used to solve complex problems. For example, an accurate numerical breast model can provide assistance to surgeons with visual information of the breast as a result of a…
Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…
This paper investigates quantum machine learning to optimize the beamforming in a multiuser multiple-input single-output downlink system. We aim to combine the power of quantum neural networks and the success of classical deep neural…
Hybrid Quantum-Classical Machine Learning (ML) is an emerging field, amalgamating the strengths of both classical neural networks and quantum variational circuits on the current noisy intermediate-scale quantum devices. This paper performs…
Most deep learning pipelines are built on real-valued operations to deal with real-valued inputs such as images, speech or music signals. However, a lot of applications naturally make use of complex-valued signals or images, such as MRI or…
This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin…
Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…
Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep Filtering (DF) was proposed to directly estimate a complex filter in frequency domain to…
Speech enhancement methods based on deep learning have surpassed traditional methods. While many of these new approaches are operating on the wideband (16kHz) sample rate, a new fullband (48kHz) speech enhancement system is proposed in this…
The ability of deep convolutional neural networks (CNN) to learn discriminative spectro-temporal patterns makes them well suited to environmental sound classification. However, the relative scarcity of labeled data has impeded the…
Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Networks (RCNN) with…
Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we introduce the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly,…
There are few knowledge representation (KR) techniques available for efficiently representing knowledge. However, with the increase in complexity, better methods are needed. Some researchers came up with hybrid mechanisms by combining two…