Related papers: Zero Aware Configurable Data Encoding by Skipping …
End-to-end neural diarization (EEND) with self-attention directly predicts speaker labels from inputs and enables the handling of overlapped speech. Although the EEND outperforms clustering-based speaker diarization (SD), it cannot be…
This paper investigates delay-distortion-power trade offs in transmission of quasi-stationary sources over block fading channels by studying encoder and decoder buffering techniques to smooth out the source and channel variations. Four…
Our paper presents solutions using erasure coding, parallel connections to storage cloud and limited chunking (i.e., dividing the object into a few smaller segments) together to significantly improve the delay performance of uploading and…
We propose a new coding scheme, called the delayed coding (DC) scheme, for channels with insertion, deletion, and substitution (IDS) errors. The proposed scheme employs delayed encoding and non-iterative detection and decoding strategies to…
Spatially-coupled (SC) codes are a class of low-density parity-check (LDPC) codes that have excellent performance thanks to the degrees of freedom they offer. An SC code is designed by partitioning a base matrix into components, the number…
In this paper we estimate the performance of 2*4 MIMO-MC-CDMA system using convolution code in MATLAB which highly reduces BER. MC-CDMA (Multi Carrier Code Division for Multiple Access) is a multiuser and multiple access system which is…
Future communication networks are expected to connect massive distributed artificial intelligence (AI). Exploiting aligned priori knowledge of AI pairs, it is promising to convert high-dimensional data transmission into highly-compressed…
Link adaptation, in particular adaptive coded modulation (ACM), is a promising tool for bandwidth-efficient transmission in a fading environment. The main motivation behind employing ACM schemes is to improve the spectral efficiency of…
Dynamic DNN optimization techniques such as layer-skipping offer increased adaptability and efficiency gains but can lead to i) a larger memory footprint as in decision gates, ii) increased training complexity (e.g., with non-differentiable…
Dataset condensation, a concept within data-centric learning, efficiently transfers critical attributes from an original dataset to a synthetic version, maintaining both diversity and realism. This approach significantly improves model…
Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…
Quantum error correction (QEC) is essential for reliable quantum information processing. Targeting a particular error channel, both the encoding and the recovery channel can be optimized through a biconvex optimization to give a…
Electrodermal activity (EDA) is widely used in wearable Internet of Medical Things (IoMT) systems for continuous health monitoring, including autonomic assessment. However, EDA signals are highly vulnerable to motion artifacts and…
Channel coding is vital for reliable sixth-generation (6G) data transmission, employing diverse error correction codes for various application scenarios. Traditional decoders require dedicated hardware for each code, leading to high…
Due to increasing cache sizes and large leakage consumption of SRAM device, conventional SRAM caches contribute significantly to the processor power consumption. Recently researchers have used non-volatile memory devices to design caches,…
Zeroth-order (ZO) optimization is being recognized as a simple yet powerful alternative to standard backpropagation (BP)-based training. Notably, ZO optimization allows for training with only forward passes and (almost) the same memory as…
Automatic differentiation (AD) is a critical step in physics-informed machine learning, required for computing the high-order derivatives of network output w.r.t. coordinates of collocation points. In this paper, we present a novel and…
Datacenters (DCs), deployed in a large scale to support the ever increasing demand for data processing applications, consume tremendous energy. Powering DCs with renewable energy can effectively reduce the brown energy consumption. Owing to…
Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environments. Sparse neural networks significantly alleviate these…
A new class of exact-repair regenerating codes is constructed by stitching together shorter erasure correction codes, where the stitching pattern can be viewed as block designs. The proposed codes have the "help-by-transfer" property where…