convolutional neural network
PulseAugur coverage of convolutional neural network — every cluster mentioning convolutional neural network across labs, papers, and developer communities, ranked by signal.
17 day(s) with sentiment data
-
New physics-guided CNN predicts complex system evolution
Researchers have developed a new physics-guided convolutional neural network designed to predict the evolution of complex physical systems. This attention-based model is trained to accurately forecast the spatiotemporal…
-
Deep learning aids design of compact, wideband power amplifiers
Researchers have developed a novel deep learning approach to design compact and wideband inverted Doherty power amplifiers. By combining convolutional neural networks (CNNs) and genetic algorithms (GAs), the method gene…
-
New LFNet method fuses CNN and SSM features for improved salient object detection
Researchers have developed a novel method called Liquid Fusion Network (LFNet) to improve salient object detection by harmonizing features from different neural network architectures. LFNet addresses the spectral biases…
-
New event-based system accurately estimates ball spin in real-time
Researchers have developed an event-based active vision system designed to accurately estimate the spin of balls in real-time across various professional sports. This system utilizes an event camera for high temporal re…
-
New optoelectronic system slashes data needs for robotic defect detection
Researchers have developed a novel hardware-software system for robotic visual inspection that significantly reduces data requirements for spatial defect detection. This system utilizes an optoelectronic architecture wh…
-
New framework enhances fetal ultrasound segmentation with semi-supervised learning
Researchers have developed DACL, a novel semi-supervised framework designed to improve the segmentation of fetal ultrasound images. This method utilizes both a lightweight convolutional network and a Transformer-based n…
-
CNNs improve blood flow simulation accuracy with physics-aware constraints
Researchers have developed a novel method for simulating blood flow in arteries using convolutional neural networks (CNNs) combined with domain decomposition. This approach, which incorporates a physics-aware constraint…
-
Hybrid deep learning method improves laser wavefront reconstruction
Researchers have developed a novel hybrid method for reconstructing wavefront distortions in laser systems, aiming to improve efficiency and accuracy. This approach combines a convolutional neural network for initial es…
-
Transformer vs CNNs: Colorectal Histology Classification Benchmark
A new study published on arXiv compares the performance of convolutional neural networks (CNNs), transformer-based models, and hybrid architectures for classifying colorectal histology images. The research evaluated twe…
-
XConv reduces convolutional neural network memory usage with compressed activations
Researchers have developed XConv, a novel approach to training convolutional neural networks that significantly reduces memory requirements. By compressing intermediate activations and approximating gradients, XConv off…
-
Machine learning revolutionizes exoplanet detection with JWST and Ariel data
A new review paper details the integration of machine learning and deep learning techniques into exoplanet detection and atmospheric characterization, driven by advancements from the James Webb Space Telescope and the u…
-
REViT: New Vision Transformer Achieves Roto-reflection Equivariance
Researchers have introduced REViT, a novel vision transformer that incorporates roto-reflection equivariance and convolutional attention. This approach aims to preserve rotational and flip symmetries in feature maps, wh…
-
New research explains why deep neural networks learn features consistently
Researchers have established feature-learning consistency guarantees for a specific class of deep neural networks (DNNs) known as sublinearly structured DNNs. These networks, characterized by input/output dimensions and…
-
Wearable ultrasound probe enables on-device hand and wrist motion tracking
Researchers have developed a novel framework for tracking hand and wrist kinematics using wearable A-mode ultrasound technology. This system, named WULPUS, employs a compact convolutional neural network that can perform…
-
New XAI dataset and method enhance species distribution model interpretability
Researchers have introduced a novel approach to enhance the interpretability of complex deep learning models used for species distribution modeling (SDMs). This method employs concept-based Explainable AI (XAI) techniqu…
-
ITNet architecture unifies convolution, attention, and recurrence
Researchers have introduced ITNet, a novel neural network architecture that unifies convolution, attention, and recurrence into a single learnable integral transform. This architecture uses a learnable kernel, implement…
-
AI Backbone Explained: Energy Demands and Infrastructure Challenges
The concept of an "AI backbone" is explored, referring to the core neural network architecture that extracts features from data, particularly in computer vision with Convolutional Neural Networks (CNNs). This backbone i…
-
New method tackles data scarcity in AI fault diagnosis systems
Researchers have developed a novel approach to designing Intelligent Fault Diagnosis Systems (IFDS) that addresses the challenge of limited labeled data. The method utilizes Deep Transfer Learning (DTL) by employing a p…
-
New CNN Accelerates Topology Optimization by 97%
Researchers have developed eCNNTO, a novel element-based Convolutional Neural Network (CNN) designed to significantly accelerate topology optimization (TO) processes. This method builds upon prior work using Deep Belief…
-
Deep learning models leverage energy features for improved surface classification in robotics
Researchers have explored the use of energy-derived features for surface classification in mobile robotics, comparing their effectiveness against inertial data. Utilizing deep learning models such as CNNs, RNNs, transfo…