iNALU: Improved Neural Arithmetic Logic Unit

• URL: http://arxiv.org/abs/2003.07629v1
• Date: Tue, 17 Mar 2020 10:37:22 GMT
• Title: iNALU: Improved Neural Arithmetic Logic Unit
• Authors: Daniel Schl\"or, Markus Ring, Andreas Hotho
• Abstract summary: The recently proposed Neural Arithmetic Logic Unit (NALU) is a novel neural architecture which is able to explicitly represent the mathematical relationships by the units of the network to learn operations such as summation, subtraction or multiplication. We show that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.
• Score: 2.331160520377439
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic Logic Unit (NALU) is a novel neural architecture which is able to explicitly represent the mathematical relationships by the units of the network to learn operations such as summation, subtraction or multiplication. Although NALUs have been shown to perform well on various downstream tasks, an in-depth analysis reveals practical shortcomings by design, such as the inability to multiply or divide negative input values or training stability issues for deeper networks. We address these issues and propose an improved model architecture. We evaluate our model empirically in various settings from learning basic arithmetic operations to more complex functions. Our experiments indicate that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.

Related papers

• Optimizing Neural Network Performance and Interpretability with Diophantine Equation Encoding [0.0]
  We introduce a novel approach that enhances the precision and robustness of deep learning models. Our method integrates a custom loss function that enforces Diophantine constraints during training, leading to better generalization, reduced error bounds, and enhanced resilience against adversarial attacks.
  arXiv  Detail & Related papers  (2024-09-11T14:38:40Z)
• The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks [59.26515696183751]
  We show that algorithm discovery in neural networks is sometimes more complex. We show that even simple learning problems can admit a surprising diversity of solutions.
  arXiv  Detail & Related papers  (2023-06-30T17:59:13Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units [86.9207811656179]
  We show that memory-augmented neural networks (NNs) can achieve higher-order, memory-augmented extrapolation, stable performance, and faster convergence. Our models achieve a 1.53% average improvement over current state-of-the-art methods in equation verification and achieve a 2.22% Top-1 average accuracy and 2.96% Top-5 average accuracy for equation completion.
  arXiv  Detail & Related papers  (2021-04-07T03:50:11Z)
• A Primer for Neural Arithmetic Logic Modules [2.4278445972594525]
  This paper is the first in discussing the current state of progress of this field. Focusing on the shortcomings of the NALU, we provide an in-depth analysis to reason about design choices of recent modules. To alleviate the existing inconsistencies, we create a benchmark which compares all existing arithmetic NALMs.
  arXiv  Detail & Related papers  (2021-01-23T16:09:16Z)
• Neural Network Approximations of Compositional Functions With Applications to Dynamical Systems [3.660098145214465]
  We develop an approximation theory for compositional functions and their neural network approximations. We identify a set of key features of compositional functions and the relationship between the features and the complexity of neural networks. In addition to function approximations, we prove several formulae of error upper bounds for neural networks.
  arXiv  Detail & Related papers  (2020-12-03T04:40:25Z)
• Stability of Algebraic Neural Networks to Small Perturbations [179.55535781816343]
  Algebraic neural networks (AlgNNs) are composed of a cascade of layers each one associated to and algebraic signal model. We show how any architecture that uses a formal notion of convolution can be stable beyond particular choices of the shift operator.
  arXiv  Detail & Related papers  (2020-10-22T09:10:16Z)
• Neural Additive Models: Interpretable Machine Learning with Neural Nets [77.66871378302774]
  Deep neural networks (DNNs) are powerful black-box predictors that have achieved impressive performance on a wide variety of tasks. We propose Neural Additive Models (NAMs) which combine some of the expressivity of DNNs with the inherent intelligibility of generalized additive models. NAMs learn a linear combination of neural networks that each attend to a single input feature.
  arXiv  Detail & Related papers  (2020-04-29T01:28:32Z)
• Systematically designing better instance counting models on cell images with Neural Arithmetic Logic Units [11.864159170745893]
  We are aiming to create better generalization systems for cell counting. numerically biased units do help models to learn numeric quantities for better generalization results. Our results confirm that above stated numerically biased units does help models to learn numeric quantities for better generalization results.
  arXiv  Detail & Related papers  (2020-04-14T17:23:37Z)
• Neural Arithmetic Units [84.65228064780744]
  Neural networks can approximate complex functions, but they struggle to perform exact arithmetic operations over real numbers. We present two new neural network components: the Neural Addition Unit (NAU), which can learn exact addition and subtraction, and the Neural multiplication Unit (NMU), which can multiply subsets of a vector. Our proposed units NAU and NMU, compared with previous neural units, converge more consistently, have fewer parameters, learn faster, can converge for larger hidden sizes, obtain sparse and meaningful weights, and can extrapolate to negative and small values.
  arXiv  Detail & Related papers  (2020-01-14T19:35:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.