Neural Networks
PulseAugur coverage of Neural Networks — every cluster mentioning Neural Networks across labs, papers, and developer communities, ranked by signal.
17 天有情绪数据
-
神经网络拥有反映现实几何结构的内部世界，可实现更安全的AI。
研究人员提出，神经网络拥有反映现实世界组织方式的内部几何结构。开发承认这种神经几何学的理论和方法，可以提高可解释性、改进控制能力，并最终实现更安全、更有效的AI系统。
-
Neural networks in physics are vulnerable to hidden systematic errors
Researchers have identified a significant vulnerability in neural network models used for high-energy physics analyses. These models, while powerful, can be systematically misled by subtle input perturbations that remai…
-
Researchers draw parallels between Boltzmann machines and quantum physics path integrals
This paper draws an analogy between Boltzmann machines used in machine learning and Feynman path integrals from quantum physics. The authors suggest that hidden layers in neural networks can be viewed as discrete versio…
-
AI models learn time-inhomogeneous Markov dynamics in financial time series
Researchers have developed a new framework that uses neural networks to parameterize time-varying Markov transition matrices for financial time series. This approach aims to balance the representational power of deep le…
-
AI's impact debated: replacing engineers, boosting productivity, and disrupting academia
A YouTube video argues that the mathematical basis for AI replacing engineers is flawed, citing limitations in neural networks, hardware, and energy costs. Separately, an article discusses Eliyahu Goldratt's Theory of C…
-
Machine learning predicts topological properties using physics-informed neural networks
Researchers have developed a novel machine learning technique to predict topological properties, specifically the Euler characteristic, from images. The model generates a unit vector field from an image, which is then i…
-
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…
-
New Conformalized Percentile Interval method improves AI prediction accuracy
Researchers have developed a new method called Conformalized Percentile Interval to improve the accuracy and efficiency of predictive intervals. This technique calibrates responses using the probability integral transfo…
-
Review details multi-fidelity neural networks for composite mechanics modeling
This paper reviews multi-fidelity surrogate modeling techniques for predicting the complex properties of composite materials. It covers methods ranging from Gaussian-process-based approaches like co-Kriging to multi-fid…
-
EdgeLPR paper explores neural network precision vs performance trade-offs for LiDAR place recognition
Researchers have developed EdgeLPR, a method for efficient LiDAR-based place recognition on edge devices. The approach utilizes Bird's Eye View representations to enable lightweight image-based networks for autonomous n…
-
New methods train neural networks with non-differentiable components
Researchers have developed new methods for training neural networks that incorporate non-differentiable components, a common challenge in areas like spiking neurons or quantized layers. One approach, detailed in an arXi…
-
New research explores batch normalization's geometric impact on neural network partitions
Two new research papers explore advancements in Batch Normalization (BN) for neural networks. One paper investigates how training-time BN affects the geometric partitioning of functions in piecewise-affine networks, sug…
-
新的正则化方法提高了神经网络的性能和复杂度控制
研究人员开发了新颖的基于范数的神经网络正则化技术，旨在提高预测性能和复杂度控制。这些方法通过纳入输入特征协方差结构来扩展经典的岭和套索惩罚。一种策略修改权重衰减以考虑特征依赖性，另一种策略将 L1 稀疏性与协方差感知的 L2 正则化相结合，以获得结构化感知权重。使用模拟和真实世界数据（包括建筑制冷负荷预测和白血病细胞分类）进行的评估表明，性能得到了增强，尤其是在处理相关或高维特征时。
-
Machine learning corrects indentation size effect in steels with small datasets
Researchers have developed a data-efficient method for correcting the indentation size effect (ISE) in steels using machine learning and physics-guided augmentation. By augmenting a dataset of approximately 700 experime…
-
量子模型通过结合学习到的特征图和经典方法来增强遥感分类
研究人员探索了使用变分量子分类器（VQC）对多光谱卫星图像进行土地覆盖分类。他们的研究（重点关注 EuroSAT-MS 数据集）发现，具有线性读出的 VQC 在性能上并未超越 RBF-SVM 等经典方法。然而，当将量子训练的特征图集成到经典基于核的决策框架中时，性能得到了显著提升。研究结果表明，将学习到的量子特征图与经典决策机制相结合，比直接替换经典模型能带来更切实的优势。
-
Researchers co-learn physics-informed AI models and controllers for energy-shaping systems
Researchers have developed a new physics-informed learning framework designed to improve energy-shaping control for port-Hamiltonian systems. This framework simultaneously learns a system model and an optimal energy-bal…
-
New adaptive meta-learning SGHMC algorithm enhances Bayesian updating for structural models
Researchers have developed a new adaptive meta-learning stochastic gradient Hamiltonian Monte Carlo (AM-SGHMC) algorithm designed to improve Bayesian updating of structural dynamic models. This method utilizes adaptive …
-
Research links neural networks, ODEs, and polynomial maps to primitive recursion
A new paper explores the computational capabilities of recurrent neural networks, polynomial ordinary differential equations (ODEs), and discrete polynomial maps. The research establishes equivalent characterizations fo…
-
Researchers pinpoint origin of neural network 'Edge of Stability' phenomenon
Researchers have introduced a new concept called the 'edge coupling' to explain the phenomenon known as the Edge of Stability in neural network training. This functional, applied to consecutive iterate pairs, helps to e…
-
Geoffrey Hinton said machine learning would outperform radiologists by now
Geoffrey Hinton's 2016 prediction that AI would surpass radiologists within five years has not materialized, according to a physician in residency. Despite significant advancements and numerous AI-enabled medical device…