Deep Neural Networks
PulseAugur coverage of Deep Neural Networks — every cluster mentioning Deep Neural Networks across labs, papers, and developer communities, ranked by signal.
16 day(s) with sentiment data
-
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…
-
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…
-
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 …
-
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…
-
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…
-
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 …
-
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 …
-
Neuromorphic depth estimation uses event cameras with uncertainty modeling
Researchers have developed a neuromorphic approach to monocular depth estimation using event cameras, which offer advantages like high temporal resolution and dynamic range. Their deep neural network models predict per-…
-
New methods improve Laplace approximation for neural network uncertainty
Researchers have developed new methods for approximating the Laplace approximation in deep neural networks, addressing the computational challenges of inverting large Hessian matrices. The proposed Gradient-Laplace and …
-
PoTAcc pipeline accelerates power-of-two quantized DNNs on edge devices
Researchers have developed PoTAcc, an open-source pipeline designed to accelerate the deployment of power-of-two (PoT) quantized deep neural networks (DNNs) on resource-constrained edge devices. This system facilitates …
-
New dynamic self-optimizing control method uses deep neural networks
Researchers have introduced a new framework for dynamic self-optimizing control, extending the concept to dynamic processes beyond steady-state applications. The paper proposes "dynamic controlled variables" (DCVs) and …
-
New AdaLoc method secures adaptable AI model usage control
Researchers have developed a new method called AdaLoc to enhance the security of deep neural networks (DNNs) by embedding an access key within a subset of the model's parameters. This approach allows for adaptable model…
-
Researchers explore neural network complexity, computation, and graph theory connections
Researchers are exploring new theoretical frameworks and computational models for neural networks. One paper introduces a unified framework to analyze and construct deep neural networks by modeling tensor operations, re…
-
Researchers develop BadSNN to exploit spiking neuron hyperparameters for backdoor attacks
Researchers have developed "BadSNN," a novel backdoor attack targeting Spiking Neural Networks (SNNs). This attack exploits variations in the hyperparameters of spiking neurons, such as the Leaky Integrate-and-Fire mode…
-
Deep Neural Networks Achieve Universality via Lindeberg Exchange Principle
Researchers have developed a new approach to understand the behavior of deep neural networks in their infinite-width limit. By applying a Lindeberg principle specifically adapted for deep neural networks, they can quant…
-
Researchers develop PyFair framework for testing neural network individual fairness
Researchers have developed PyFair, a new framework designed to formally assess and verify individual fairness in deep neural networks. This system adapts concolic testing techniques to systematically explore network beh…
-
New 'sphere cloud' method enhances privacy in 3D visual localization
Researchers have developed a novel privacy-preserving technique for visual localization using a "sphere cloud" representation. This method addresses concerns about deep neural networks reconstructing private maps from 3…
-
New VCON framework enables smooth, iterative DNN compression with minimal accuracy loss
Researchers have introduced Vanishing Contributions (VCON), a novel framework designed to streamline the process of compressing deep neural networks. VCON enables a smoother, iterative transition to compressed models by…
-
Deep neural networks provably overcome curse of dimensionality for PDEs
Researchers have demonstrated that deep neural networks (DNNs) can overcome the curse of dimensionality when approximating solutions to Kolmogorov partial differential equations. This mathematical proof extends previous…
-
AI paradigm discovers explainable scientific equations, outperforming deep learning
Researchers have introduced a new paradigm called machine collective intelligence, designed to autonomously discover governing equations from empirical data. This approach combines symbolic reasoning with metaheuristics…