Unsupervised pre-trained filter learning approach for efficient convolution neural network

S ur Rehman, S Tu, M Waqas, Y Huang, O ur Rehman… - Neurocomputing, 2019 - Elsevier
Abstract The concept of Convolution Neural Network (ConvNet or CNN) is evaluated from
the animal visual cortex. Since humans can learn through experience, similarly, ConvNet …

Distributed Task Processing Platform for Infrastructure-less IoT Networks: A Multi-dimensional Optimisation Approach

Q Zheng, J **, Z Shen, L Wu, I Ahmad… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
With the rapid development of artificial intelligence (AI) and the Internet of Things (IoT),
intelligent information services have showcased unprecedented capabilities in acquiring …

Deep networks for image-to-image translation with mux and demux layers

H Liu, P Navarrete Michelini… - Proceedings of the …, 2018 - openaccess.thecvf.com
Imageprocessingmethodsusingdeepconvol… have achieved great successes on
quantitative and qualitative assessments in many tasks, such as super–resolution, style …

[PDF][PDF] Lightweight transfer learning models for ultrasound-guided classification of COVID-19 patients

ME Karar, O Reyad, M Abd-Elnaby… - Comput. Mater …, 2021 - cdn.techscience.cn
Lightweight deep convolutional neural networks (CNNs) present a good solution to achieve
fast and accurate image-guided diagnostic procedures of COVID-19 patients. Recently …

Deep learning models for intelligent healthcare: implementation and challenges

S Rehman, S Tu, Z Shah, J Ahmad, M Waqas… - Artificial Intelligence and …, 2021 - Springer
The rapid developments of artificial intelligent (AI) is being transformed for its extensive use-
cases, people-centered intelligent systems focusing on care delivery, research encounter …

DSFEC: Efficient and Deployable Deep Radar Object Detection

G Dandugula, S Boddana, S Mirashi - arxiv preprint arxiv:2412.07411, 2024 - arxiv.org
Deploying radar object detection models on resource-constrained edge devices like the
Raspberry Pi poses significant challenges due to the large size of the model and the limited …

SelectQ: Calibration Data Selection for Post-Training Quantization

Z Zhang, Y Gao, J Fan, Z Zhao, Y Yang… - Machine Intelligence …, 2025 - mi-research.net
Post-training quantization (PTQ) can reduce the memory footprint and latency of deep model
inference while still preserving the accuracy of model, with only a small unlabeled …

Merging-and-evolution networks for mobile vision applications

Z Qin, Z Zhang, S Zhang, H Yu, Y Peng - IEEE Access, 2018 - ieeexplore.ieee.org
Compact neural networks are inclined to exploit “sparsely-connected” convolutions, such as
depthwise convolution and group convolution for employment in mobile applications …

Method of transmitting and merging data

YS Lin, WC Chen, TPC Chen - US Patent App. 17/165,096, 2022 - Google Patents
US20220156551A1 - Method of transmitting and merging data - Google Patents
US20220156551A1 - Method of transmitting and merging data - Google Patents Method of …

Condense-expansion-depth-wise convolutional neural network for face recognition

Y Chen, J Li - US Patent 11,823,033, 2023 - Google Patents
Techniques related to implementing convolutional neural networks for face or other object
recognition are discussed. Such techniques may include applying, in turn, a depth-wise …