CNN
PulseAugur coverage of CNN — every cluster mentioning CNN across labs, papers, and developer communities, ranked by signal.
- founded by Ted Turner 100%
- subsidiary of Warner Bros. Discovery 100%
- subsidiary of WarnerMedia 100%
- founded Ted Turner 95%
- instance of computed tomography 90%
- founded WarnerMedia 90%
- instance of convolutional neural network 90%
- instance of Mauritius 90%
- founded Fortune 90%
- used by Convolutional Block Attention Module 90%
- instance of GradCAM 90%
- used by Vít 70%
22 day(s) with sentiment data
-
New S2P-Net architecture offers rotation-invariant object recognition
Researchers have developed S2P-Net, a novel deep learning architecture designed for rotation-invariant object recognition, particularly in scenarios with limited data. This network achieves guaranteed rotation invarianc…
-
Robotics motion feasibility prediction improved with new Transformer model
Researchers have developed a new method for predicting motion feasibility in robotics, particularly for cluttered environments. This approach uses a point-cloud-based Transformer architecture, named GRASPFC-PTX, to lear…
-
REViT imbues Vision Transformers with rotation equivariance without position encoding
Researchers have developed REViT, a novel approach that imbues Vision Transformers (ViTs) with rotation and reflection equivariance without relying on complex position encodings. By utilizing a 'Lifting' layer and Group…
-
New framework uses AI for structural damage diagnosis with limited data · 3 sources tracked
Researchers have developed a novel multi-fidelity transfer learning framework for structural health monitoring using guided waves. This approach combines lightweight physics-based simulations with convolutional autoenco…
-
Linear models with optimized preprocessing match advanced architectures in time-series forecasting
Researchers propose that optimizing preprocessing, rather than scaling model architectures, can significantly improve time-series forecasting accuracy. Using Ridge regression as a testbed, they found that optimal lookba…
-
Larry Ellison donates $45M to pro-Trump group amid Oracle's AI buildout wins
Larry Ellison, co-founder of Oracle, has quietly donated approximately $45 million to a nonprofit organization supporting Donald Trump's campaign. This undisclosed funding contrasts with the more public engagements of o…
-
New AI models use respiratory signals for stress and emotion detection
Researchers have developed a novel approach to recognizing affective and stress states using respiratory signals, combining convolutional neural networks (CNNs) with handcrafted respiratory features. The study found tha…
-
New Diffusion Model Enhances MRI Scan Resolution with Structural Guidance
Researchers have developed MR-DiffuSR, a novel 3D latent diffusion model designed to enhance the resolution of FLAIR MRI scans. This framework utilizes cross-modality structural guidance from HR T1w images to prevent th…
-
New metric quantifies AI model vulnerability to hardware faults
Researchers have developed a new metric called Parameter Vulnerability Factor (PVF) to quantify the susceptibility of AI models to hardware faults, specifically silent data corruptions (SDCs). This metric aims to standa…
-
Hybrid CNN-LSTM model boosts cybersecurity for renewable energy grids
Researchers have developed a novel hybrid CNN-LSTM framework designed to enhance cybersecurity in smart renewable energy grids. This model effectively detects both immediate anomalies and gradual, low-and-slow attack ca…
-
Savannah Guthrie begs for help finding missing mother amid ransom note reports
Savannah Guthrie, host of the "Today" show, has made an emotional plea for public assistance in the search for her missing mother, Nancy Guthrie, 84. Reports have emerged detailing ransom notes received by media outlets…
-
AI deciphers ancient scroll carbonized by Vesuvius eruption · 4 sources tracked
Advanced imaging technology and AI techniques have successfully deciphered text from a papyrus scroll carbonized during the eruption of Mount Vesuvius nearly 2,000 years ago. Researchers virtually unrolled the scroll, r…
-
New framework tackles asymmetric blur in smartphone stereo cameras
Researchers have introduced a new framework and dataset for addressing heterogeneous stereo deblurring, a problem arising from hardware variations in smartphone cameras that cause asymmetric blur. The proposed physicall…
-
AI Model Explained: LLM, Transformer, Diffusion, and More
This article explains various types of AI models, differentiating between Dense models and Mixture of Experts (MoE) for Large Language Models (LLMs). It details the Transformer architecture, which is foundational to mod…
-
New method achieves linear complexity for remote sensing instance segmentation
Researchers have developed RS4D, a novel method for instance segmentation in remote sensing imagery that utilizes distilled state space modeling (SSM) to achieve linear computational complexity. This approach addresses …
-
Missing woman's family in agony after ransom note suggests she is dead
The family of missing 84-year-old Nancy Guthrie is in agony after receiving a ransom note indicating she is dead. Her daughter, Savannah Guthrie, a host on the "Today" show, made an emotional plea for information, stati…
-
Prediction markets draw scrutiny over election influence and national security risks
Prediction markets, platforms where users can bet on future events, are raising concerns about their potential impact on national security and U.S. politics. These markets, which differ from traditional gambling by havi…
-
New SPOFA framework stabilizes heterogeneous knowledge distillation
Researchers have developed SPOFA, a new framework designed to stabilize heterogeneous knowledge distillation (HKD). HKD aims to transfer knowledge between different model architectures, such as Transformers and CNNs, bu…
-
MambaADv2 framework enhances unsupervised anomaly detection with Mamba architecture
Researchers have introduced MambaADv2, a novel framework for unsupervised anomaly detection that leverages Mamba-based architectures. This approach aims to overcome the limitations of CNNs and Transformers by combining …
-
New framework uses hierarchical RL for neural network compression
Researchers have developed HiReLC, a hierarchical reinforcement learning framework designed to jointly quantize and prune deep neural networks. This approach uses low-level agents for per-kernel configurations and high-…