deep neural network
PulseAugur coverage of deep neural network — every cluster mentioning deep neural network across labs, papers, and developer communities, ranked by signal.
- developed ScienceCast 90%
- instance of CORE Recommender 90%
- instance of deep learning 90%
- instance of convolutional neural network 90%
- instance of DagsHub 70%
- instance of Gotit.pub 70%
- instance of alphaXiv 70%
- used by Gotit.pub 70%
- used by deep learning 70%
- used by ScienceCast 70%
- instance of CatalyzeX 70%
- used by DagsHub 60%
9 day(s) with sentiment data
-
New method offers statistical and privacy guarantees for deep regression models
Researchers have developed a method to provide statistical and privacy guarantees for deep non-parametric regression models trained using Stochastic Gradient Langevin Dynamics (SGLD). By employing a PAC-Bayesian analysi…
-
New framework enhances DNA methylation tumor classification with OOD detection
Researchers have developed a new framework to improve the robustness of DNA methylation-based tumor classification systems. This deep representation learning approach focuses on detecting out-of-distribution (OOD) sampl…
-
Deep learning framework enhances DNA methylation tumor classification robustness
Researchers have developed a novel deep representation learning framework to improve the robustness of DNA methylation-based tumor classifiers against out-of-distribution (OOD) data. The proposed method extracts feature…
-
New transfer learning framework boosts VLC indoor localization accuracy
Researchers have developed a novel transfer learning framework to improve indoor localization accuracy in Visible Light Communication (VLC) systems, particularly for Industry 4.0 applications. This framework significant…
-
New framework boosts indoor localization accuracy for Industry 4.0
Researchers have developed a new transfer learning framework to improve the accuracy and data efficiency of Visible Light Communication (VLC)-based indoor localization systems, which are crucial for Industry 4.0 applica…
-
New Theorem Proves Gradient Trajectory Convergence in Deep Neural Networks
A new paper published on arXiv introduces a theorem that addresses the gradient conjecture at infinity for definable potentials. The research proves that gradient trajectories of such potentials have finite spherical le…
-
New ODE-based method advances conditional distribution learning
Researchers have introduced Conditional Föllmer Flow, a novel deep generative method based on ordinary differential equations (ODEs) for learning conditional distributions. This method starts with a standard Gaussian di…
-
New criterion optimizes weight initialization for deep neural networks
Researchers have developed a new mathematical criterion for selecting the optimal variance of weight initialization in deep neural networks (DNNs). By analyzing stochastic gradient descent (SGD) through a continuous-tim…
-
New research explores advanced quantization for edge AI accelerators
Two new research papers explore advanced quantization techniques for deep neural networks (DNNs) on edge devices. The first paper introduces ShiftQAT, a quantization-aware training flow for the MAX7800x family of CNN ac…
-
WisdomNet architecture aims for error-free AI classification
Researchers have introduced WisdomNet, a novel neural network architecture designed to achieve error-free classification. This approach prompts the model to indicate when it cannot confidently make a decision, thereby a…
-
Kuaishou deploys new retrieval model to boost video watch time
Researchers have developed a Controllable Retrieval Model (CRM) designed to enhance efficiency in recommendation systems by incorporating desired watch times as a condition. This framework, implemented using both deep n…
-
New research explores subspace optimization for efficient LLM training · 2 sources tracked
Two new research papers explore advanced optimization techniques for training large language models (LLMs) more efficiently. The first paper introduces SMRC and PMRC, which use a residual correction framework to maintai…
-
Deep learning enhances seismic interference removal in large-scale Angola survey
Researchers have applied a deep neural network (DNN) to significantly improve seismic interference attenuation in a large-scale marine seismic survey in Angola's Camie Field. This DNN-based workflow, trained using a sup…
-
Deep neural network framework simplifies AC power flow contingency analysis
Researchers have developed a novel framework for AC power flow contingency analysis that utilizes a single deep neural network (DNN) to predict post-contingency operating states. This approach aims to reduce the computa…
-
New DPG loss functions enhance neural network accuracy for PDEs
Researchers have developed new residual-based loss functions for machine learning models that aim to accurately predict solutions for parameter-dependent partial differential equations (PDEs). These functions, particula…
-
FPGA platform accelerates approximate multiplier evaluation for DNNs
Researchers have developed FAME, a new platform utilizing FPGAs to accelerate the evaluation of approximate multipliers for deep neural networks. This hardware-based approach significantly reduces the time needed to ass…
-
OptiPrime framework optimizes private DNN inference with protocol-hardware co-design
Researchers have developed OptiPrime, a framework designed to improve the efficiency of private deep neural network (DNN) inference. This framework addresses the latency issues associated with hybrid homomorphic encrypt…
-
Deep learning model predicts ocean currents for plastic debris cleanup
Researchers have developed Drift Field Net (DFN), a deep neural network designed to predict ocean surface flow fields using satellite observations. This model aims to improve forecasts of particle drift, crucial for str…
-
NeuroFlex enables lossless ANN-SNN co-execution for efficient sparse inference
Researchers have developed NeuroFlex, a novel accelerator design that allows for the co-execution of artificial neural networks (ANNs) and spiking neural networks (SNNs) at the element level. This approach enables each …
-
Research paper details temperature effects on analog DNN inference
A new research paper explores the impact of temperature on analog deep neural network (DNN) inference, particularly for resource-constrained devices like mobile phones. The study found that temperature significantly deg…