Related papers: Joint Model and Data Driven Receiver Design for Da…

The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based…

In time-varying fading channels, channel coefficients are estimated using pilot symbols that are transmitted every coherence interval. For channels with high Doppler spread, the rapid channel variations over time will require considerable…

Unsupervised and supervised learning methods conventionally use kernels to capture nonlinearities inherent in data structure. However experts have to ensure their proposed nonlinearity maximizes variability and capture inherent diversity of…

Quantum-inspired tensor networks algorithms have shown to be effective and efficient models for machine learning tasks, including anomaly detection. Here, we propose a highly parallelizable quantum-inspired approach which we call SMT-AD…

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…

While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads to severe performance degradation when dataset shift…

Domain adaption (DA) and domain generalization (DG) are two closely related methods which are both concerned with the task of assigning labels to an unlabeled data set. The only dissimilarity between these approaches is that DA can access…

This paper presents an unsupervised multi-modal learning system that learns associative representation from two input modalities, or channels, such that input on one channel will correctly generate the associated response at the other and…

The acquisition of Downlink (DL) channel state information at the transmitter (CSIT) is known to be a challenging task in multiuser massive MIMO systems when uplink/downlink channel reciprocity does not hold (e.g., in frequency division…

While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power. Training…

This paper presents a large-system analysis of the performance of joint channel estimation, multiuser detection, and per-user decoding (CE-MUDD) for randomly-spread multiple-input multiple-output (MIMO) direct-sequence code-division…

Deep learning based PET image reconstruction methods have achieved promising results recently. However, most of these methods follow a supervised learning paradigm, which rely heavily on the availability of high-quality training labels. In…

We propose a novel learning-based framework for image reconstruction particularly designed for training without ground truth data, which has three major building blocks: energy-based learning, a patch-based Wasserstein loss functional, and…

Linear block transform coding remains a fundamental component of image and video compression. Although the Discrete Cosine Transform (DCT) is widely employed in all current compression standards, its sub-optimality has sparked ongoing…

We propose a joint channel estimation and data detection (JED) algorithm for densely-populated cell-free massive multiuser (MU) multiple-input multiple-output (MIMO) systems, which reduces the channel training overhead caused by the…

Deep learning algorithms have shown tremendous success in many recognition tasks; however, these algorithms typically include a deep neural network (DNN) structure and a large number of parameters, which makes it challenging to implement…

In this paper, we consider the joint design of the transceivers for a multiple access Multiple Input and Multiple Output (MIMO) system having Inter-Symbol Interference (ISI) channels. The system we consider is equipped with the Minimum Mean…

Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for the entire training process as well as inference. Dynamic sparse training (DST), as a leading sparse training approach, can…

We develop a pragmatic multi-user (MU) massive multiple-input multiple-output (MIMO) channel model tailored to the THz band, encompassing factors such as molecular absorption, reflection losses and multipath diffused ray components. Next,…

Recognizing symmetries in data allows for significant boosts in neural network training. In many cases, however, the underlying symmetry is present only in an idealized dataset, and is broken in the training data, due to effects such as…