News

Microsoft, OpenAI and Anthropic are investing millions to train teachers how to use AI
A group of leading tech companies is teaming up with two teachers’ unions to train 400,000 kindergarten through 12th grade teachers in artificial intelligence over the next five years.
Data Pipelines For AI Agents: Building The Backbone Of Intelligent Automation
The infrastructure behind AI agents isn't static—it’s a living, evolving system. Designing effective data pipelines means ...
IEEE2d
Dynamic Semantic Compression for CNN Inference in Multi-Access Edge Computing: A Graph Reinforcement Learning-Based Autoencoder - IEEE Xplore
This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and edge servers’ available ...
IEEE3d
M-net: A Convolutional Neural Network for deep brain structure segmentation - IEEE Xplore
In this paper, we propose an end-to-end trainable Convolutional Neural Network (CNN) architecture called the M-net, for segmenting deep (human) brain structures from Magnetic Resonance Images (MRI). A ...
IEEE5d
Multi-Stream 1D CNN for EEG Motor Imagery Classification of Limbs Activation - IEEE Xplore
In this paper, a novel multi-stream 1D Convolutional Neural Network (CNN) architecture is proposed. The input EEG signal is processed by four convolutional streams, which differ in the size of ...
IEEE5d
BEFNet: A Hybrid CNN-Mamba Architecture for Accurate Skin Lesion Image Segmentation - IEEE Xplore
Accurate image segmentation of skin lesions is crucial for the detection and treatment of skin cancer. Based on the modern state space model Mamba, a novel hybrid CNN-Mamba network (BEFNet) is ...
IEEE6d
Real time lane detection using CNN - IEEE Xplore
Road lane detection plays a crucial role in advancing autonomous driving technologies, enhancing vehicle safety, and contributing to intelligent transportation systems. This paper proposes a road lane ...
IEEE8d
Guided CNN Restoration with Explicitly Signaled Linear Combination
State-of-the-art Convolutional Neural Network (CNN) based loop restoration generally involves a CNN structure with a large number of parameters and applies the CNN model to those degraded frames ...
IEEE9d
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices - IEEE Xplore
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new ...
IEEE10d
Radial Basis Function Networks for Convolutional Neural Networks to Learn Similarity Distance Metric and Improve Interpretability - IEEE Xplore
The specific architecture of RBFs enables the learning of a similarity distance metric to compare and find similar and dissimilar images. Furthermore, we demonstrate that using an RBF classifier on ...
IEEE12d
Dunstan Baby Language Classification with CNN - IEEE Xplore
The database loaded with the sounds made by Romanian babies was labelled by doctors in the maternity hospitals and two Dunstan experts, separately. Finally, the results of the CNN automatic ...
IEEE12d
Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance Applications - IEEE Xplore
Convolutional neural networks (CNNs) have yielded state-of-the-art performance in image classification and other computer vision tasks. Their application in fire detection systems will substantially ...