Related papers: Pruning-aware Loss Functions for STOI-Optimized Pr…
Advancements in clinical Brain-Computer Interfaces (BCIs) depend on precise and reliable signal interpretation. However, the high-dimensional and noisy nature of data captured from both implanted and non-implanted BCIs poses significant…
Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness remains poorly understood. We conduct a controlled empirical study of three…
Deploying an end-to-end automatic speech recognition (ASR) model on mobile/embedded devices is a challenging task, since the device computational power and energy consumption requirements are dynamically changed in practice. To overcome the…
To fully unlock the benefits of multiple-input multiple-output (MIMO) networks, downlink channel state information (CSI) is required at the base station (BS). In frequency division duplex (FDD) systems, the CSI is acquired through a…
Physics-informed neural networks (PINNs) provide a promising framework for solving inverse problems governed by partial differential equations (PDEs) by integrating observational data and physical constraints in a unified optimization…
Sensitivity to ITDs is important for sound localization. Normal-hearing listeners benefit from across-frequency processing, as seen with improved ITD thresholds when consistent ITD cues are presented over a range of frequency channels…
Deep-neural-network (DNN) based noise suppression systems yield significant improvements over conventional approaches such as spectral subtraction and non-negative matrix factorization, but do not generalize well to noise conditions they…
Retinal implants aim to restore functional vision despite photoreceptor degeneration, yet are fundamentally constrained by low resolution electrode arrays and patient-specific perceptual distortions. Most deployed encoders rely on…
Interference alignment (IA) is a linear precoding strategy that can achieve optimal capacity scaling at high SNR in interference networks. Most of the existing IA designs require full channel state information (CSI) at the transmitters,…
Objective: This work aims to demonstrate a low-power, biomimetic auditory sensing concept for fully implantable cochlear implants. The approach draws inspiration from the frequency selectivity and temporal encoding of the cochlea, and uses…
This study presents a parameter-light, low-complexity artificial intelligence/machine learning (AI/ML) model that enhances channel state information (CSI) feedback in wireless systems by jointly exploiting temporal, spatial, and frequency…
Auditory models are commonly used as feature extractors for automatic speech-recognition systems or as front-ends for robotics, machine-hearing and hearing-aid applications. Although auditory models can capture the biophysical and nonlinear…
The widespread availability of pre-trained vision models has enabled numerous deep learning applications through their transferable representations. However, their computational and storage costs often limit practical deployment.…
Structured pruning is a promising approach to create smaller, faster large language models. However, existing methods typically rely on computing the gradient via backward passes, which can inflate memory requirements and compute costs. In…
EIE proposed to accelerate pruned and compressed neural networks, exploiting weight sparsity, activation sparsity, and 4-bit weight-sharing in neural network accelerators. Since published in ISCA'16, it opened a new design space to…
Coordinated beamforming (Co-BF) is a key multi-access-point coordination (MAPC) technique for dense Wi-Fi deployments, but its performance can be hindered by the large channel state information (CSI) feedback required through channel…
Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing…
Neural network compression has gained increasing attention in recent years, particularly in computer vision applications, where the need for model reduction is crucial for overcoming deployment constraints. Pruning is a widely used…
Neural network pruning with suitable retraining can yield networks with considerably fewer parameters than the original with comparable degrees of accuracy. Typical pruning methods require large, fully trained networks as a starting point…
The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one or more of the…