← Back to all news
arXiv Machine Learning By Andrzej Odrzywo{\l}ek

Diversity of EML-type operators

Read the original on arXiv Machine Learning →

The article "Diversity of EML-type operators" discusses the EML operator, which can evaluate standard explicit purely transcendental elementary functions, and notes that while most research has focused on the binary EML, many similar variants exist. It enumerates and classifies these variants, clarifies common misconceptions, and proposes a M"obius layer that replaces matrix operations with rational functions. The paper also showcases the activation function eml(x,1/x), enabling separate recovery of exp(x) and ln(x) and thus evaluation of all elementary functions within a rational neural‑network generalization.

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 Machine Learning.

Related stories

Hugging Face Trending Papers
Jun 22

EML Trees Are Universal Approximators

The recently introduced EML (Exp-Minus-Log) function acts as continuous analogue of NAND gates, providing a compositional building block capable of representing elementary functions. In this work, we study the expressive power of tree-structured compositions of EML functions.

More like this →
arXiv AI
Jul 13

All you need is SAMPAT

arXiv:2607. 09235v1 Announce Type: cross Abstract: The current state of the art in AI/ML rests on deep neural architectures, which, in general, suffer from a lack of interpretability.

By Jayadeva, Madhur Aswani
benchmarkssafety
More like this →
arXiv Machine Learning
5d ago

NeuralCert: certified computational discovery of extremal mathematical constructions

NeuralCert presents a framework that learns high‑dimensional variational trial functions in a compact separable form, then spectrally diagnoses, prunes, and exactly certifies them via multimodular evaluation. The method is fully explicit and independently verifiable, and can run on a standard personal computer. Applied to three extremal problems, it demonstrates that neural optimization can discover better constructions, reveal empirical invariants useful for proofs, and expose optimization barriers that inspire new analytic or numerical approaches.

By Mark Patrick Roeling
More like this →
arXiv Machine Learning
Jun 25

Rational Neural Networks have Expressivity Advantages

arXiv:2602. 12390v2 Announce Type: replace Abstract: We study neural networks with trainable low-degree rational activation functions and show that they are more expressive and parameter-efficient than modern piecewise-linear and smooth activations such as ELU, LeakyReLU, LogSigmoid, PReLU, ReLU, SELU, CELU, Sigmoid, SiLU, Mish, Softplus, Tanh, Softmin, Softmax, and LogSoftmax.

By Maosen Tang, Alex Townsend
llms
More like this →
arXiv AI
Sep 4

Complete Identification of Deep ReLU Networks through {\L}ukasiewicz Logic

The paper presents a complete characterization of when two deep ReLU networks realize the same function, showing that this occurs iff one can be transformed into the other using a set of axioms from many‑valued logic. It introduces a symbolic calculus that maps networks to substitution graphs, proves a completeness theorem linking equivalent formulas, and provides an algorithm to reconstruct networks from these graphs. The framework yields a new compositional normal form for MV logic that preserves the algebraic structure of deep ReLU networks.

By Yani Zhang, Helmut B\"olcskei
robotics
More like this →