Advanced Hybridization and Optimization of DNNs for Medical Imaging: A Survey on Disease Detection Techniques
Sign Up to like & getrecommendations! Published in 2025 at "Artificial Intelligence Review"
DOI: 10.1007/s10462-024-11049-x
Abstract: Due to the high classification accuracy and fast computational speed offered by Deep Neural Networks (DNNs), they have been widely used for the design and development of automated Artificial Intelligence (AI) tools for the detection… read more here.
Keywords: methodology; dnns; disease detection; review ... See more keywords
Cooperative Inference of DNNs for Delay- and Memory-Constrained Wireless IoT Systems
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2022.3152359
Abstract: This work studies the cooperative inference of deep neural networks (DNNs), in which a memory-constrained end device performs a delay-constrained inference process with an aid of an edge server. Although several works considered the cooperative… read more here.
Keywords: memory constrained; inference; memory; cooperative inference ... See more keywords
TIMAQ: A Time-Domain Computing-in-Memory-Based Processor Using Predictable Decomposed Convolution for Arbitrary Quantized DNNs
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Journal of Solid-State Circuits"
DOI: 10.1109/jssc.2021.3095232
Abstract: Energy-efficient processors are crucial for accelerating deep neural networks (DNNs) on edge devices with limited battery capacity. To reduce energy consumption, time-domain computing-in-memory (TD-CIM) is a splendid architecture, which consumes low computation and memory access… read more here.
Keywords: energy; quantization; time; dnns ... See more keywords
Power Law in Deep Neural Networks: Sparse Network Generation and Continual Learning With Preferential Attachment.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3217403
Abstract: Training deep neural networks (DNNs) typically requires massive computational power. Existing DNNs exhibit low time and storage efficiency due to the high degree of redundancy. In contrast to most existing DNNs, biological and social networks… read more here.
Keywords: preferential attachment; power law; power; dnns ... See more keywords
Noise-Tolerant CIM-DNNs Explained.
Sign Up to like & getrecommendations! Published in 2025 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2025.3621473
Abstract: Compute-in-memory (CIM) systems implemented with resistive random access memory (RRAM) crossbars are a promising approach for accelerating deep neural network (DNN) computations. However, it is noteworthy that RRAM-based CIM systems are susceptible to computational errors.… read more here.
Keywords: vat; noise tolerant; dnns; cim dnns ... See more keywords
Spherical DNNs and Their Applications in 360 ° Images and Videos.
Sign Up to like & getrecommendations! Published in 2021 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2021.3100259
Abstract: Spherical images or videos, as typical non-Euclidean data, are usually stored in the form of 2D panoramas obtained through an equirectangular projection, which is neither equal area nor conformal. The distortion caused by the projection… read more here.
Keywords: images videos; spherical dnns; dnns; saliency detection ... See more keywords