arXiv AI
Aug 12
Entropy-Centric Explainable AI for Remote Sensing Image Segmentation
arXiv:2608. 11064v1 Announce Type: cross Abstract: Artificial intelligence (AI) has become a powerful approach to solving complex problems in critical domains.
Learning Entropy and Spatial Adaptation Dynamics of Multilayer Perceptrons for Structural Point Extraction
arXiv:2606. 10170v1 Announce Type: new Abstract: This paper extends the concept of Learning Entropy (LE) from temporal adaptive systems to spatial learning in multilayer perceptron networks (MLPs) applied to image data.
Related stories
arXiv AI
Sep 1
Understanding Deep Learning via Entropy Space Theory
arXiv:2608.29279v1 Announce Type: new Abstract: Deep learning is often criticized for its theoretical research lagging behind practice. To make deep learning easier to understand, the entropy space t...
arXiv Machine Learning
Sep 11
Revenge of Monosemanticity: Neuron Specialization as a New Form of Feature Learning in MLPs
The paper investigates how multilayer perceptrons (MLPs) learn features in regression tasks with clustered data. It finds that instead of forming a single global low‑dimensional representation, MLPs develop monosemantic specialized neurons—each neuron aligns strongly with a specific predictive feature relevant to a particular region of the input space. This specialization results in a collection of local low‑dimensional representations, giving MLPs a provable data‑efficiency advantage over methods that rely on a global representation.
arXiv Machine Learning
Aug 26
Revenge of Monosemanticity: Specialized Neurons Improve Data Efficiency in MLPs
arXiv:2608.24007v1 Announce Type: new Abstract: Understanding how neural networks learn and organize features is central to understanding their behavior. Much existing theory of feature learning has...
arXiv Machine Learning
Oct 3
Generalization in Neural Networks Through the Lens of Magnitude Potential
The paper introduces magnitude potential, a metric derived from metric magnitude theory, to assess how well a point is represented by a set. By computing the ratio of magnitude potential relative to a class versus the entire dataset at the logit layer, the authors find correlations with Feldman memorization scores and detect structural changes in decision boundaries, including grokking in modular arithmetic. This ratio remains informative even when neural collapse is suppressed, highlighting its robustness in capturing intra‑ and inter‑class geometric structure.
Hugging Face Trending Papers
Aug 13
TabSOM: A tabular-to-image encoding method based on self-organizing maps
Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers. They convert tabular data into image representations, mapping each feature at a fixed pixel location derived from a dimensionality-reduction method (e.
arXiv Computer Vision
Sep 22
Transferring Visual Explanations: How Cross-Architecture Knowledge Distillation Affects Model Interpretability
arXiv:2609.23561v1 Announce Type: new Abstract: Deploying efficient neural networks is essential in resource-constrained environments, yet compact models often sacrifice interpretability - a critical...
arXiv AI
1d ago
Rescuing Points Trapped Inside Incorrect Decision Regions: A target for Evaluating and Improving Forward-Forward Learning
arXiv:2610.16347v1 Announce Type: cross Abstract: Forward-Forward learning replaces end-to-end backpropagation with local, layer-wise training objectives. Its variants are evaluated primarily by clas...
arXiv Machine Learning
Sep 11
Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution
The paper investigates a spatial-concentration bias in Evolvable-Substrate HyperNEAT (ES‑HyperNEAT) when applied to MNIST, where evolved networks focus on a central cluster of input pixels. By partitioning the input image into 13 non‑overlapping spatial segments and evolving a separate expert network for each, the authors achieve a 43% mean accuracy—an 106% relative improvement over the baseline—without relying on data‑driven weighting. The study also introduces a receptive‑field diagnostic to detect silent input‑coverage collapse and a spatial‑partitioning remedy to restore full image coverage.
arXiv AI
Jun 10
Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification
arXiv:2411. 05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification.
arXiv AI
Oct 1
From Dataset Spectral Geometry to Network Weights: A Geometry-Aware Initialization for Sigmoidal MLPs in Image Classification
arXiv:2606.28444v2 Announce Type: replace-cross Abstract: Classical universal approximation theorems (UAT) establish the expressive power of sigmoidal multilayer perceptrons, but they do not specify...
arXiv Machine Learning
Jun 2
Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures
arXiv:2606. 00557v1 Announce Type: new Abstract: To understand how a neural network (NN) functions and makes predictions, it has become increasingly clear that analyzing only the input domain is insufficient -- one must also examine its internal inference mechanisms to capture the complete picture.