English
Related papers

Related papers: Neural Arithmetic Logic Units

200 papers

We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is…

Neural and Evolutionary Computing · Computer Science 2014-12-11 Alex Graves , Greg Wayne , Ivo Danihelka

A general procedure for introducing parametric, learned, nonlinearity into activation functions is found to enhance the accuracy of representative neural networks without requiring significant additional computational resources. Examples…

Machine Learning · Computer Science 2025-05-14 David Yevick

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

It has been widely assumed that a neural network cannot be recovered from its outputs, as the network depends on its parameters in a highly nonlinear way. Here, we prove that in fact it is often possible to identify the architecture,…

Machine Learning · Computer Science 2020-02-25 David Rolnick , Konrad P. Kording

The dominant paradigm in modern neural networks relies on simple, monotonically-increasing activation functions like ReLU. While effective, this paradigm necessitates large, massively-parameterized models to approximate complex functions.…

Machine Learning · Computer Science 2025-08-27 Shiko Kudo

Artificial neural networks which are inspired from the learning mechanism of brain have achieved great successes in many problems, especially those with deep layers. In this paper, we propose a nucleus neural network (NNN) and corresponding…

Computer Vision and Pattern Recognition · Computer Science 2019-05-15 Jia Liu , Maoguo Gong , Haibo He

We propose the Moderate Adaptive Linear Unit (MoLU), a novel activation function for deep neural networks, defined analytically as: f(x)=x \times (1+tanh(x))/2. MoLU combines mathematical elegance with empirical effectiveness, exhibiting…

Machine Learning · Computer Science 2025-07-16 Hankyul Koh , Joon-hyuk Ko , Wonho Jhe

We characterise the computational power of recurrent graph neural networks (GNNs) in terms of arithmetic circuits over the real numbers. Our networks are not restricted to aggregate-combine GNNs or other particular types. Generalising…

Computational Complexity · Computer Science 2026-05-05 Timon Barlag , Vivian Holzapfel , Laura Strieker , Jonni Virtema , Heribert Vollmer

Artificial neural networks have been proposed as potential algorithms that could benefit from being implemented and run on quantum computers. In particular, they hold promise to greatly enhance Artificial Intelligence tasks, such as image…

Quantum Physics · Physics 2021-03-04 Stefano Mangini , Francesco Tacchino , Dario Gerace , Chiara Macchiavello , Daniele Bajoni

Our theoretical understanding of deep learning has not kept pace with its empirical success. While network architecture is known to be critical, we do not yet understand its effect on learned representations and network behavior, or how…

Machine Learning · Computer Science 2022-07-22 Andrew M. Saxe , Shagun Sodhani , Sam Lewallen

Universal approximation theorem suggests that a shallow neural network can approximate any function. The input to neurons at each layer is a weighted sum of previous layer neurons and then an activation is applied. These activation…

Machine Learning · Computer Science 2020-10-30 Bhaavan Goel

A wide variety of activation functions have been proposed for neural networks. The Rectified Linear Unit (ReLU) is especially popular today. There are many practical reasons that motivate the use of the ReLU. This paper provides new…

Machine Learning · Statistics 2020-10-19 Rahul Parhi , Robert D. Nowak

Natural Language Understanding (NLU) is a branch of Natural Language Processing (NLP) that uses intelligent computer software to understand texts that encode human knowledge. Recent years have witnessed notable progress across various NLU…

Computation and Language · Computer Science 2022-03-01 Xinliang Frederick Zhang

Symbolic rule learners generate interpretable solutions, however they require the input to be encoded symbolically. Neuro-symbolic approaches overcome this issue by mapping raw data to latent symbolic concepts using a neural network.…

Machine Learning · Computer Science 2023-10-10 Theo Charalambous , Yaniv Aspis , Alessandra Russo

Deep neural networks with millions of parameters are at the heart of many state of the art machine learning models today. However, recent works have shown that models with much smaller number of parameters can also perform just as well. In…

Machine Learning · Computer Science 2016-08-03 Suraj Srinivas , R. Venkatesh Babu

Employing equivariance in neural networks leads to greater parameter efficiency and improved generalization performance through the encoding of domain knowledge in the architecture; however, the majority of existing approaches require an a…

Machine Learning · Computer Science 2023-05-31 Emmanouil Theodosis , Karim Helwani , Demba Ba

A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing…

Machine Learning · Computer Science 2022-06-23 Alex Bäuerle , Daniel Jönsson , Timo Ropinski

Deep neural networks typically treat nonlinearities as fixed primitives (e.g., ReLU), limiting both interpretability and the granularity of control over the induced function class. While recent additive models (like KANs) attempt to address…

Machine Learning · Computer Science 2026-02-05 Jusheng Zhang , Ningyuan Liu , Qinhan Lyu , Jing Yang , Keze Wang

For neural networks (NNs) with rectified linear unit (ReLU) or binary activation functions, we show that their training can be accomplished in a reduced parameter space. Specifically, the weights in each neuron can be trained on the unit…

Machine Learning · Statistics 2020-01-30 Tong Qin , Ling Zhou , Dongbin Xiu

Artificial neural networks are simple and efficient machine learning tools. Defined originally in the traditional setting of simple vector data, neural network models have evolved to address more and more difficulties of complex real world…

Neural and Evolutionary Computing · Computer Science 2012-10-26 Marie Cottrell , Madalina Olteanu , Fabrice Rossi , Joseph Rynkiewicz , Nathalie Villa-Vialaneix