Related papers: Transfer Learning Enabled Transformer based Genera…
One of the most significant challenges in statistical signal processing and machine learning is how to obtain a generative model that can produce samples of large-scale data distribution, such as images and speeches. Generative Adversarial…
State-of-the-art methods for image-to-image translation with Generative Adversarial Networks (GANs) can learn a mapping from one domain to another domain using unpaired image data. However, these methods require the training of one specific…
We demonstrate machine learning (ML) based reconstruction of terahertz transmission spectra using an electrically tunable grating-gate AlGaN/GaN plasmonic-crystal analyzer. The analyzer encodes the transmission spectrum into a…
Image super-resolution aims to synthesize high-resolution image from a low-resolution image. It is an active area to overcome the resolution limitations in several applications like low-resolution object-recognition, medical image…
The ever-increasing demand for high-speed data transmission continues to motivate research and development efforts towards the sixth generation (6G) of wireless communication technologies and beyond. The use of terahertz (THz) carrier…
Generative adversarial networks (GANs) are widely used for distribution learning, yet their classical formulations remain theoretically fragile, with ill-posed objectives, unstable training dynamics, and limited interpretability. In this…
In this article, we develop an end-to-end wireless communication system using deep neural networks (DNNs), in which DNNs are employed to perform several key functions, including encoding, decoding, modulation, and demodulation. However, an…
Recent works have demonstrated the superiority of supervised Convolutional Neural Networks (CNNs) in learning hierarchical representations from time series data for successful classification. These methods require sufficiently large labeled…
Many real-world tasks are plagued by limitations on data: in some instances very little data is available and in others, data is protected by privacy enforcing regulations (e.g. GDPR). We consider limitations posed specifically on…
Accurate channel modeling is fundamental to design and evaluation of Terahertz (THz) ultra-massive multiple-input multiple-output (UM-MIMO) systems. However, existing model-based approaches typically rely on simplified assumptions, such as…
An efficient channel estimation is of vital importance to help THz communication systems achieve their full potential. Conventional uplink channel estimation methods, such as least square estimation, are practically inefficient for THz…
Sub-Terahertz (THz) frequencies between 100 GHz and 300 GHz are being considered as a key enabler for the sixth-generation (6G) wireless communications due to the vast amounts of unused spectrum. The 3rd Generation Partnership Project…
We introduce the GANformer, a novel and efficient type of transformer, and explore it for the task of visual generative modeling. The network employs a bipartite structure that enables long-range interactions across the image, while…
Generative Adversarial Networks (GANs) have proven to be a powerful tool in generating artistic images, capable of mimicking the styles of renowned painters, such as Claude Monet. This paper introduces a tiered GAN model to progressively…
Generative Adversarial Networks (GANs) have extended deep learning to complex generation and translation tasks across different data modalities. However, GANs are notoriously difficult to train: Mode collapse and other instabilities in the…
End-to-end, autoregressive model-based TTS has shown significant performance improvements over the conventional one. However, the autoregressive module training is affected by the exposure bias, or the mismatch between the different…
Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data. Other astonishing results have been achieved using neural nets as data generators,…
Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the datasets of some specific scenes or applications. If we train…
Terahertz (THz) band communications is envisioned as a key technology for future wireless standards. Substantial progress has been made in this field, with advances in hardware design, channel models, and signal processing. High-rate…
Terahertz communications are envisioned as a key enabler for 6G networks. The abundant spectrum available in such ultra high frequencies has the potential to increase network capacity to huge data rates. However, they are extremely affected…