English
Related papers

Related papers: iNALU: Improved Neural Arithmetic Logic Unit

200 papers

Human learning thrives on the ability to learn from mistakes, adapt through feedback, and refine understanding-processes often missing in static machine learning models. In this work, we introduce Composite Learning Units (CLUs) designed to…

Machine Learning · Computer Science 2024-10-11 Santosh Kumar Radha , Oktay Goktas

Prevailing deep models are single-purpose and overspecialize at individual tasks. However, when being extended to new tasks, they typically forget previously learned skills and learn from scratch. We address this issue by introducing…

Computation and Language · Computer Science 2022-05-10 Fan Zhang , Duyu Tang , Yong Dai , Cong Zhou , Shuangzhi Wu , Shuming Shi

Deep neural networks (DNNs) have garnered significant attention in various fields of science and technology in recent years. Activation functions define how neurons in DNNs process incoming signals for them. They are essential for learning…

Machine Learning · Computer Science 2023-08-31 Jianfei Li , Han Feng , Ding-Xuan Zhou

Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks. However, because of the zero-hard rectification, ReLU networks miss the benefits from negative values. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2018-01-30 Suo Qiu , Xiangmin Xu , Bolun Cai

We derive upper bounds on the complexity of ReLU neural networks approximating the solution of a linear system given the matrix and the right-hand side. We focus on matrices which are symmetric positive definite and sparse, as they appear…

Numerical Analysis · Mathematics 2026-03-20 Benjamin Dörich , Roland Maier , Lukas Ullmer

We study optimization problems where the objective function is modeled through feedforward neural networks with rectified linear unit (ReLU) activation. Recent literature has explored the use of a single neural network to model either…

Machine Learning · Computer Science 2022-05-11 Keliang Wang , Leonardo Lozano , Carlos Cardonha , David Bergman

Recurrent Neural Networks (RNNs) are used to learn representations in partially observable environments. For agents that learn online and continually interact with the environment, it is desirable to train RNNs with real-time recurrent…

Machine Learning · Computer Science 2024-10-31 Esraa Elelimy , Adam White , Michael Bowling , Martha White

Deep neural networks have recently achieved state-of-the-art results in many machine learning problems, e.g., speech recognition or object recognition. Hitherto, work on rectified linear units (ReLU) provides empirical and theoretical…

Machine Learning · Computer Science 2015-05-12 Jakub Mikolaj Tomczak

A possible path to the interpretability of neural networks is to (approximately) represent them in the regional format of piecewise linear functions, where regions of inputs are associated to linear functions computing the network outputs.…

Logic in Computer Science · Computer Science 2025-06-09 Sandro Preto , Marcelo Finger

The notion of equality (identity) is simple and ubiquitous, making it a key case study for broader questions about the representations supporting abstract relational reasoning. Previous work suggested that neural networks were not suitable…

Machine Learning · Computer Science 2022-05-03 Atticus Geiger , Alexandra Carstensen , Michael C. Frank , Christopher Potts

Activation functions play a critical role in deep neural networks by shaping gradient flow, optimization stability, and generalization. While ReLU remains widely used due to its simplicity, it suffers from gradient sparsity and dead-neuron…

Machine Learning · Computer Science 2025-12-03 Ashkan Shakarami , Yousef Yeganeh , Azade Farshad , Lorenzo Nicolè , Stefano Ghidoni , Nassir Navab

Neural networks leverage robust internal representations in order to generalise. Learning them is difficult, and often requires a large training set that covers the data distribution densely. We study a common setting where our task is not…

Neural algorithmic reasoning aims to capture computations with neural networks by training models to imitate the execution of classical algorithms. While common architectures are expressive enough to contain the correct model in the weight…

Machine Learning · Computer Science 2025-08-14 Gleb Rodionov , Liudmila Prokhorenkova

Neural networks may naturally favor distance-based representations, where smaller activations indicate closer proximity to learned prototypes. This contrasts with intensity-based approaches, which rely on activation magnitudes. To test this…

Machine Learning · Computer Science 2025-02-05 Alan Oursland

Large language models (LLMs) can solve an increasing number of complex reasoning tasks while making surprising mistakes in basic numerical understanding and processing (such as 9.11 > 9.9). The latter ability is essential for tackling…

Computation and Language · Computer Science 2025-03-06 Haotong Yang , Yi Hu , Shijia Kang , Zhouchen Lin , Muhan Zhang

Artificial Intelligence agents are required to learn from their surroundings and to reason about the knowledge that has been learned in order to make decisions. While state-of-the-art learning from data typically uses sub-symbolic…

Artificial Intelligence · Computer Science 2021-12-24 Samy Badreddine , Artur d'Avila Garcez , Luciano Serafini , Michael Spranger

We find arithmetic ability resides within a limited number of attention heads, with each head specializing in distinct operations. To delve into the reason, we introduce the Comparative Neuron Analysis (CNA) method, which identifies an…

Computation and Language · Computer Science 2024-09-24 Zeping Yu , Sophia Ananiadou

This article is concerned with the approximation and expressive powers of deep neural networks. This is an active research area currently producing many interesting papers. The results most commonly found in the literature prove that neural…

Machine Learning · Computer Science 2019-05-08 I. Daubechies , R. DeVore , S. Foucart , B. Hanin , G. Petrova

When optimizing a nonlinear objective, one can employ a neural network as a surrogate for the nonlinear function. However, the resulting optimization model can be time-consuming to solve globally with exact methods. As a result, local…

Optimization and Control · Mathematics 2026-03-19 Jiatai Tong , Yilin Zhu , Thiago Serra , Samuel Burer

We introduce exact macroscopic on-line learning dynamics of two-layer neural networks with ReLU units in the form of a system of differential equations, using techniques borrowed from statistical physics. For the first experiments,…

Machine Learning · Computer Science 2019-03-19 Michiel Straat , Michael Biehl