Related papers: Advanced Machine Learning Techniques for Self-Inte…
We investigate the complexity of deep neural networks through the lens of functional equivalence, which posits that different parameterizations can yield the same network function. Leveraging the equivalence property, we present a novel…
Due to the Internet of Things (IoT) proliferation, Radio Frequency (RF) channels are increasingly congested with new kinds of devices, which carry unique and diverse communication needs. This poses complex challenges in modern digital…
Modern deep learning has enabled unprecedented achievements in various domains. Nonetheless, employment of machine learning for wave function representations is focused on more traditional architectures such as restricted Boltzmann machines…
Deep neural networks (DNNs) are increasingly being used in a variety of traditional radiofrequency (RF) problems. Previous work has shown that while DNN classifiers are typically more accurate than traditional signal processing algorithms,…
In next-generation communications, massive machine-type communications (mMTC) induce severe burden on base stations. To address such an issue, automatic modulation classification (AMC) can help to reduce signaling overhead by blindly…
Accelerated magnetic resonance (MR) scan acquisition with compressed sensing (CS) and parallel imaging is a powerful method to reduce MR imaging scan time. However, many reconstruction algorithms have high computational costs. To address…
Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the…
Artificial neural networks can be trained with relatively low-precision floating-point and fixed-point arithmetic, using between one and 16 bits. Previous works have focused on relatively wide-but-shallow, feed-forward networks. We…
Continual learning is the sequential learning of different tasks by a machine learning model. Continual learning is known to be hindered by catastrophic interference or forgetting, i.e. rapid unlearning of earlier learned tasks when new…
In Machine Learning, Artificial Neural Networks (ANNs) are a very powerful tool, broadly used in many applications. Often, the selected (deep) architectures include many layers, and therefore a large amount of parameters, which makes…
Radar sensors are gradually becoming a wide-spread equipment for road vehicles, playing a crucial role in autonomous driving and road safety. The broad adoption of radar sensors increases the chance of interference among sensors from…
Recent advances in learning-based image compression typically come at the cost of high complexity. Designing computationally efficient architectures remains an open challenge. In this paper, we empirically investigate the impact of…
Advantages of deep learning over traditional methods have been demonstrated for radio signal classification in the recent years. However, various researchers have discovered that even a small but intentional feature perturbation known as…
Deep learning has revolutionized industries like computer vision, natural language processing, and speech recognition. However, back propagation, the main method for training deep neural networks, faces challenges like computational…
Binary Neural Networks (BNNs) enable efficient deep learning by saving on storage and computational costs. However, as the size of neural networks continues to grow, meeting computational requirements remains a challenge. In this work, we…
Seismic processing often requires suppressing multiples that appear when collecting data. To tackle these artifacts, practitioners usually rely on Radon transform-based algorithms as post-migration gather conditioning. However, such…
The brain cortex, which processes visual, auditory and sensory data in the brain, is known to have many recurrent connections within its layers and from higher to lower layers. But, in the case of machine learning with neural networks, it…
Reduced precision computation for deep neural networks is one of the key areas addressing the widening compute gap driven by an exponential growth in model size. In recent years, deep learning training has largely migrated to 16-bit…
We consider artificial neurons which will update their weight coefficients with an internal rule based on backpropagation, rather than using it as an external training procedure. To achieve this we include the backpropagation error estimate…
The Dual-Path Convolution Recurrent Network (DPCRN) was proposed to effectively exploit time-frequency domain information. By combining the DPRNN module with Convolution Recurrent Network (CRN), the DPCRN obtained a promising performance in…