artificial neural network
PulseAugur coverage of artificial neural network — every cluster mentioning artificial neural network across labs, papers, and developer communities, ranked by signal.
9 天有情绪数据
-
New research advances adversarial imitation learning theory and practice
Two new papers explore the theoretical underpinnings of adversarial imitation learning (AIL), a technique that uses neural networks to learn from expert demonstrations. The first paper introduces OPT-AIL, a framework de…
-
New ADANNs method enhances deep learning for parametric partial differential equations
Researchers have introduced Algorithmically Designed Artificial Neural Networks (ADANNs), a novel deep learning approach for approximating operators related to parametric partial differential equations. This method comb…
-
Spiking neural networks on Intel Loihi 2 achieve energy-efficient real-time object detection
Researchers have developed a method for designing and deploying Spiking Neural Networks (SNNs) for real-time object detection on edge neuromorphic hardware, specifically the Intel Loihi 2 processor. Their work demonstra…
-
机器学习以 92% 的准确率绘制 Vicsek 模型相图
研究人员采用机器学习技术绘制了 Vicsek 群集模型的相图。通过分析模拟数据并使用 K-Means 聚类，他们将数据点分类为无序、有序或共存相。然后，他们在一个神经网络上训练了这些分类，在预测相行为方面达到了 0.92 的准确率，并扩展了已知的相边界。
-
AI approach enhances variable selection in linear regression models
Researchers have developed a novel Artificial Intelligence approach for variable selection in linear regression models. This method utilizes an Artificial Neural Network (ANN) trained to assess variable significance bas…
-
Deep-testing: the case of dependence detection
Researchers have introduced a new method called deep-testing, which applies deep learning techniques to the statistical problem of hypothesis testing. This approach uses a neural network trained on simulated data to act…
-
Two-person company designs, builds, and tests novel aerospike rocket engine in weeks using AI
A two-person company rapidly designed, built, and tested an aerospike rocket engine in just a few weeks, a process that previously took years and large teams. The company utilized a neural network, which they term "comp…
-
ML guides primal heuristics for complex mixed binary quadratic programs
Researchers have developed new machine learning-guided primal heuristics to tackle Mixed Binary Quadratic Programs (MBQPs), a complex class of optimization problems. This work introduces a novel neural network architect…
-
联邦学习进展在隐私、效用和公平性之间取得平衡
研究人员正在探索增强联邦学习（FL）隐私的高级技术，FL是一种在去中心化数据上进行模型训练的方法。一项研究比较了在瑞典医疗保健数据上用于心血管疾病风险建模的差分隐私（DP）和同态加密（HE），发现HE与集中式方法相当，但计算开销更高，而DP在某些模型上表现出更大的性能下降。另一种方法FedPF引入了一种差分隐私的公平FL算法，通过将公平性和效用视为竞争目标来平衡它们，在具有竞争力的准确性和低计算占用的情况下显著减少了歧视。第三篇论文将…
-
Researchers use generative modeling to solve quantum dynamics via score matching
Researchers have developed a novel method to solve the time-dependent Schrödinger equation by learning the score function on Bohmian trajectories. This approach utilizes a neural network to parametrize the score and min…
-
Photonic processors offer energy-efficient alternative for deep learning computations
The future of deep learning may involve photonic processors that use light instead of electrons to perform calculations. This approach aims to reduce the significant energy demands of current neural networks, which rely…
-
DAIRE AI model offers real-time detection of vehicle network attacks
Researchers have developed DAIRE, a lightweight AI model designed to detect and classify cyberattacks on the Controller Area Network (CAN) within the Internet of Vehicles (IoV). This framework utilizes a specialized art…
-
Onyx offers cost-efficient, disk-oblivious ANN search for sensitive data
Researchers have developed Onyx, a new system for approximate nearest neighbor (ANN) search designed to protect sensitive data when processed on external storage. Onyx addresses the high costs and latency associated wit…
-
Dyna语言连接逻辑编程与机器学习研究
Dyna是一种专为机器学习研究人员设计的新型编程语言，旨在弥合数学概念与可执行代码之间的差距。它建立在Datalog和Prolog等逻辑编程范式的基础上，引入了灵活的执行顺序和加权规则等功能。这使得能够用最少的代码简洁地表达复杂的算法，包括矩阵乘法、斐波那契数列和神经网络。