Manchester Literary and Philosophical Society
PulseAugur coverage of Manchester Literary and Philosophical Society — every cluster mentioning Manchester Literary and Philosophical Society across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New method aligns neural network weights, reducing barriers in NeRF models
Researchers have developed a new method called Progressive Permutation Alignment with Temperature-Controlled Spectral Sharpening to address the challenge of permutation symmetry in implicit neural representations (INRs)…
-
VeilNN framework enhances edge neural network security against adversarial attacks
Researchers have developed VeilNN, a new defense framework designed to protect neural networks deployed on edge devices from cross-node adversarial attacks. This framework introduces controlled diversity in models throu…
-
New G^2MLP framework distills graph geometry from GNNs to MLPs
Researchers have developed a new distillation framework called Graph Geometry-aware MLP (G^2MLP) to improve the performance of MLPs when trained using knowledge from Graph Neural Networks (GNNs). Existing methods often …
-
Researchers use hyperbolic geometry to explain deep network training dynamics
A new research paper introduces a novel approach to understanding the training dynamics of deep neural networks by representing them in hyperbolic geometry. The method constructs temporal parameter graphs, which are sna…
-
Airfoil2Vec: Neural surrogate models accelerate aerodynamic predictions
Researchers have developed Airfoil2Vec, a novel neural surrogate model designed to predict airfoil aerodynamics with significant speedups over traditional computational fluid dynamics methods. This model utilizes spectr…
-
RecMorph architecture advances generalized morphology control in robotics
Researchers have developed RecMorph, a novel topology-guided spatial recurrent architecture designed for generalized morphology control in robotics. This architecture uses recurrent sequence computation to facilitate cr…
-
Grokking transition in neural networks quantified, data complexity key
Researchers have quantified the transition from memorization to generalization in neural networks, a phenomenon known as grokking. They discovered a power-law scaling relation for the onset time of grokking, indicating …
-
New research details label flipping attacks on distributed ML systems
A new research paper explores the potential harm of gradient attacks in distributed machine learning systems, specifically focusing on label flipping. The study proposes a formalization of these attacks as a constrained…
-
New NAS methods optimize neural networks for compactness and performance
Researchers have developed a new framework for Neural Architecture Search (NAS) that uses continuous relaxations to optimize neural network architectures more efficiently. This approach, which includes methods like NAS-…
-
New research uses persistent homology to analyze AI model topology
Researchers have analyzed the topology of learned representations within predictive coding networks (PCNs), a neuro-inspired bidirectional architecture. Using persistent homology on PCNs trained on synthetic data and MN…
-
CASA-SDF framework enhances 3D reconstruction for indoor scenes
Researchers have introduced CASA-SDF, a novel framework for high-fidelity 3D reconstruction in indoor environments. This approach tackles the challenge of geometric heterogeneity by employing a curriculum-aware spatial …
-
MetaNCA learns to self-organize neural network weights
Researchers have introduced Meta Neural Cellular Automata (MetaNCA), a novel framework designed to learn local rules that can self-organize the weights of artificial neural networks. This approach utilizes a learned rul…
-
Neural network symmetry readout depends on positional encoding
A new paper explores how the symmetries within neural network weights are influenced by the positional encoding (PE) and the specific readout methods used for analysis. Researchers found that the PE can obscure or revea…
-
Spiking Neural Network Achieves In-Context Learning with Single Layer
Researchers have developed DendriCL, a novel single-layer spiking neural network architecture that demonstrates in-context learning (ICL) capabilities. Unlike existing AI models that rely on deep architectures and impli…
-
New S-GAI framework embeds dataset geometry into MLP weights
Researchers have developed S-GAI, a novel initialization framework for sigmoidal MLPs that embeds dataset geometry directly into network weights. This method uses singular value decomposition (SVD) to estimate class-wis…
-
Full-resolution MLPs outperform CNNs and transformers in medical dense prediction
Researchers have developed a new framework for medical dense prediction tasks that utilizes Multi-layer Perceptrons (MLPs) at full image resolution. This approach aims to overcome limitations of Convolutional Neural Net…
-
GS-KAN offers parameter-efficient alternative to Kolmogorov-Arnold Networks
Researchers have introduced GS-KAN, a novel architecture that enhances the efficiency of Kolmogorov-Arnold Networks (KANs). By utilizing shared basis functions and learnable linear transformations, GS-KAN significantly …
-
New PURe Networks Explicitly Model Nonlinear Feature Interactions
Researchers have introduced Product-Unit Residual Networks (PURe) to better model nonlinear feature interactions in scientific and engineering applications. These networks integrate multiplicative product units with res…
-
Neural implicit learning reconstructs 3D geometry from RF signals
Researchers have developed GeRaF, a novel method for 3D geometry reconstruction using radio frequency (RF) signals. This approach leverages neural implicit learning to overcome the challenges of low resolution and noise…
-
New Ansatz Predicts Bayesian Deep Neural Network Performance
Researchers have developed a new approximate method to predict the generalization performance of Bayesian deep neural networks (MLPs) with fixed depth. The approach utilizes an equivalent Wishart Ansatz to model the flu…