← Back to all news
arXiv AI By Tiansi Dong, Mateja Jamnik, Pietro Li\`o

Non-Zero Radius: The Missing Component of Neural Networks

Read the original on arXiv AI →

The paper proposes Sphere Neural Networks (SphNNs), which replace the conventional zero‑radius vector representation with spheres of non‑zero radius to better capture biological cognition and enable symbolic reasoning. By relaxing the zero‑radius constraint, the authors argue that concepts can be represented as spatial regions, allowing reasoning through model construction and inspection. SphNNs employ a transition map that achieves Aristotelian syllogistic reasoning without training data, aiming to address the black‑box nature and symbolic reasoning limitations of current neural networks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 15

Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks

The paper introduces a flexible symbolic framework that efficiently computes logical explanations for deep neural networks by parameterizing explanations with internal neuron activations and leveraging general-purpose logical engines like SMT solvers. Unlike previous methods that rely on specialized verifiers or are limited to individual input features, this approach is not restricted in shape and can scale to deep architectures. Experiments on image recognition and medical benchmarks demonstrate improved computational efficiency and the ability to explain networks that were previously intractable for logic-based methods.

By Tom\'a\v{s} Kol\'arik, Faezeh Labbaf, Fabrizio Leopardi, Grigory Fedyukovich, Michael Wand, Natasha Sharygina
computer-visionbenchmarks
More like this →
arXiv AI
2d ago

Predicate Neuron: Differentiable Quantization of Predicate Relations in Gradient-based Learning

The paper introduces the Native Predicate Neuron, a differentiable logic‑reasoning module that can be inserted into standard neural architectures. It learns to alternate between logical operations using a single trainable parameter and employs a dual‑nature gradient mechanism that performs hard logical operations during training while remaining differentiable for backpropagation. Experiments on Fully‑Connected, Convolutional, Recurrent, and Transformer models show that adding Predicate Neurons speeds convergence, improves accuracy, and reduces loss, especially on tasks involving monotonic reasoning or discontinuities.

By Ioannis Konstantoulas, Iliana Loi, Kyriakos Sgarbas
llmsefficiencybenchmarks
More like this →