mlsanityData to 14 Oct 2026

Two Instances of Interpretable Neural Network for Universal Approximations

arXiv 2112.15026 ↗First posted 30 Dec 2021cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper proposes two bottom-up interpretable neural network (NN) constructions for universal approximation, namely Triangularly-constructed NN (TNN) and Semi-Quantized Activation NN (SQANN). Further notable properties are (1) resistance to catastrophic forgetting (2) existence of proof for arbitrarily high accuracies (3) the ability to identify samples that are out-of-distribution through interpretable activation "fingerprints".

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 23 references that are in the map. First posted on arXiv 30 Dec 2021.

Builds on

10 of 23 references.

References · 10

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  3. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  4. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  5. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  6. 2019Universal Approximation with Deep Narrow Networkscited by 200
  7. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  8. 2017Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activationscited by 104
  9. 2020Minimum Width for Universal Approximationcited by 94
  10. 2018Deep, Skinny Neural Networks are not Universal Approximatorscited by 38

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Universal Approximation Theorems of Fully Connected Binarized Neural Networks
  2. 2023Q-SENN: Quantized Self-Explaining Neural Networks
  3. 2026Arbitrary-Accuracy Neural Approximation with Optimal Neuron Count and Near-Optimal Bit Complexity
  4. 2024GINN-KAN: Interpretability pipelining with applications in Physics Informed Neural Networks
  5. 2026Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
  6. 2025SAFR: Neuron Redistribution for Interpretability
  7. 2025From superposition to sparse codes: interpretable representations in neural networks
  8. 2025Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition