arXiv AI
From Dataset Spectral Geometry to Network Weights: A Geometry-Aware Initialization for Sigmoidal MLPs in Image Classification
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 30
S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights
arXiv:2606. 28444v1 Announce Type: cross Abstract: Classical universal approximation theorems establish the expressive power of sigmoidal multilayer perceptrons, but they do not prescribe how initial weights should encode the geometry of a data distribution.
arXiv Machine Learning
Jun 25
Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks
arXiv:2606. 25256v1 Announce Type: cross Abstract: We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer.
Hugging Face Trending Papers
Jun 24
Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks
We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer. Before the first forward pass, Pre-Warm extracts mean-centered local patches from a single training batch, clusters them with MiniBatchKMeans, applies inverse Manhattan spatial weighting, and uses the resulting centroids to initialize half of the first-layer filters (the remainder retain Kaiming initialization).
arXiv AI
Sep 18
Green-ELM: Efficient Analytic Learning via High-Dimensional Random Projections
arXiv:2604. 15613v4 Announce Type: replace-cross Abstract: We present Green-ELM, a non-iterative neural architecture that replaces gradient-based optimization of the output layer with a closed-form analytic solution over a fixed, high-dimensional random feature representation.
arXiv Machine Learning
Jun 4
HalfNet: Randomized Neural Networks with Learned Subspace Geometry
arXiv:2606. 04583v1 Announce Type: new Abstract: Many researchers investigated neural networks with some of their weights fixed to values randomly drawn from a given distribution, e.
arXiv Machine Learning
Sep 1
Multiclass Linear Perceptrons with Multiplicative Margins
arXiv:2608.30028v1 Announce Type: new Abstract: This paper introduces a family of multiclass linear Perceptron classifiers with a multiplicative margin mechanism (MMPerc), as an alternative to standa...