PulseAugur
实时 01:55:43
实体 Deep Neural Networks

Deep Neural Networks

PulseAugur coverage of Deep Neural Networks — every cluster mentioning Deep Neural Networks across labs, papers, and developer communities, ranked by signal.

Show in brief
总计 · 30天
36
90 天内 36
发布 · 30天
0
90 天内 0
论文 · 30天
35
90 天内 35
层级分布 · 90 天
情绪 · 30 天

5 天有情绪数据

最近 · 第 1/2 页 · 共 36 条
  1. RESEARCH · CL_48753 ·

    New RefCal framework boosts deep neural network reliability

    Researchers have developed a new framework called RefCal to improve the reliability of deep neural networks. This framework jointly optimizes accuracy, calibration, and refinement, addressing the common issue where impr…

  2. TOOL · CL_44759 ·

    Deep Neural Networks viewed as Discrete Dynamical Systems

    A new research paper proposes viewing deep neural networks (DNNs) as discrete dynamical systems, drawing parallels to neural integral equations and their PDE forms. The study compares numerical solutions of Burgers' and…

  3. TOOL · CL_43187 ·

    YouTube's AI recommendation system uses two-stage filtering

    This paper delves into YouTube's sophisticated recommendation system, highlighting its use of machine learning to personalize content for over a billion users. The system operates in two stages: candidate generation, wh…

  4. RESEARCH · CL_44074 ·

    New method generates synthetic cell videos for AI training

    Researchers have developed a new framework for generating synthetic videos of cell phantoms, which are essential for training deep neural networks in biomedical video analysis. This method utilizes Elliptical Fourier De…

  5. RESEARCH · CL_43983 ·

    New simulation models cognitive limits in speech understanding

    Researchers have developed an in silico simulation of the RAMPHO buffer, a cognitive bottleneck in multi-talker listening environments. This simulation uses phonetic entropy from the wav2vec 2.0 acoustic model to differ…

  6. TOOL · CL_42516 ·

    New framework analyzes neural network robustness to data shifts

    Researchers have developed a new framework to analyze the distributional robustness of deep neural networks, a key challenge for real-world AI deployment. The framework models interactions between layer weights and acti…

  7. RESEARCH · CL_41746 ·

    New MIST method detects Trojans in fine-tuned DNNs

    Researchers have developed a new method called MIST to detect malicious Trojans embedded in deep neural networks (DNNs) during the fine-tuning process. MIST analyzes the spectral changes in a model's internal representa…

  8. TOOL · CL_41922 ·

    New GAMR method improves deep learning with noisy labels

    Researchers have developed a new method called GAMR (Geometric-Aware Manifold Regularization) to improve deep neural network performance when trained on datasets with noisy labels. Unlike existing methods that passively…

  9. TOOL · CL_41879 ·

    New system enables large DNNs on low-RAM Android phones

    Researchers have developed a new system called CROWD IO to enable the efficient inference of large deep neural networks on resource-constrained Android devices. The system addresses the challenge of limited RAM on mobil…

  10. RESEARCH · CL_41736 ·

    New theory uses geometry to explain neural network mechanisms

    Researchers have introduced a new theoretical framework called the Pursuit of Subspaces (PoS) hypothesis to better understand the inner workings of deep neural networks. This axiomatic approach uses geometric postulates…

  11. TOOL · CL_49705 ·

    Researchers explore bidirectional knowledge transfer between Random Forests and Deep Neural Networks

    Researchers have explored bidirectional knowledge distillation between Random Forests and Deep Neural Networks, a novel approach to model compression and ensemble learning for big data. Their study introduces methods fo…

  12. TOOL · CL_38338 ·

    New theory explains deep neural network generalization via Riemannian Dimension

    Researchers have developed a new theory to explain why deep neural networks generalize, focusing on a pointwise approach for fully connected networks. This framework introduces the pointwise Riemannian Dimension, derive…

  13. RESEARCH · CL_38171 ·

    New methods boost AI interpretability and image generation efficiency

    Researchers have introduced a new parameter-free method called "aligned training" to enhance the quality and stability of sparse autoencoders (SAEs), a technique used for interpreting deep neural networks. This method a…

  14. RESEARCH · CL_38190 ·

    StatQAT paper details statistical quantizer optimization for deep networks

    Researchers have developed StatQAT, a new statistical error analysis framework for optimizing quantization in deep neural networks. This method provides theoretical insights into quantization error and introduces iterat…

  15. TOOL · CL_32743 ·

    Homological Neural Networks leverage compositional sparsity for efficient architecture design

    Researchers have developed Homological Neural Networks (HNNs) that leverage compositional sparsity as an inductive bias for designing neural architectures. These networks are significantly sparser than standard deep neu…

  16. TOOL · CL_31333 ·

    New framework RobustLT tackles adversarial training on imbalanced datasets

    Researchers have developed a new framework called RobustLT to improve adversarial training for deep neural networks, particularly on datasets with long-tail distributions. The framework addresses limitations in current …

  17. TOOL · CL_32622 ·

    Survey paper organizes research on deep learning generalization bounds

    This survey paper organizes recent research on data-dependent worst-case generalization bounds for deep neural networks. It explores how these bounds can be refined by considering the specific parts of the parameter spa…

  18. RESEARCH · CL_30566 ·

    New method analyzes neural network generalization via decision pattern shifts

    Researchers have introduced a new method called Decision Pattern Shift (DPS) to better understand why deep neural networks struggle to generalize to new data. DPS analyzes the stability of a model's internal decision-ma…

  19. RESEARCH · CL_30567 ·

    AI hallucinations in imaging linked to inverse problem limits

    Researchers have developed a theoretical framework to understand and quantify "hallucinations" in AI models used for inverse problems, such as medical imaging. The study shows that these realistic but incorrect details …

  20. TOOL · CL_29289 ·

    Study evaluates transfer learning for deep neural networks in image classification

    Researchers explored how to best select pre-trained deep neural networks for image classification tasks. They adapted eleven models, originally trained on ImageNet, to five distinct target datasets. The study evaluated …