English
Related papers

Related papers: Improving the Universality and Learnability of Neu…

200 papers

We formally define algorithmic capture of combinatorial tasks as the ability of a transformer to extrapolate to arbitrary task sizes with controllable error and logarithmic sample adaptation, providing a sharp scaling criterion for…

Machine Learning · Computer Science 2026-05-08 Orit Davidovich , Zohar Ringel

Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predictions. We propose to…

Artificial Intelligence · Computer Science 2017-07-27 Svetlin Penkov , Subramanian Ramamoorthy

We introduce a parallelizable simplification of Neural Turing Machine (NTM), referred to as P-NTM, which redesigns the core operations of the original architecture to enable efficient scan-based parallel execution. We evaluate the proposed…

Neural and Evolutionary Computing · Computer Science 2026-02-24 Gabriel Faria , Arnaldo Candido Junior

In David Schmidt's PhD work he explored the use of denotational semantics as a programming language. It was part of an effort to not only treat formal semantics as specifications but also as interpreters and input to compiler generators.…

Programming Languages · Computer Science 2013-09-23 Mads Rosendahl

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Machine Learning · Computer Science 2025-03-04 David Klindt , Charles O'Neill , Patrik Reizinger , Harald Maurer , Nina Miolane

We are entering a new era in which software systems are becoming more and more complex and larger. So, the composition of such systems is becoming infeasible by manual means. To address this challenge, self-organising software models…

Formal Languages and Automata Theory · Computer Science 2025-08-27 Damian Arellanes

To address the issues of stability and fidelity in interpretable learning, a novel interpretable methodology, ensemble interpretation, is presented in this paper which integrates multi-perspective explanation of various interpretation…

Machine Learning · Computer Science 2023-12-12 Chao Min , Guoyong Liao , Guoquan Wen , Yingjun Li , Xing Guo

In this paper we propose a compositional scheme for the construction of abstractions for networks of control systems using the interconnection matrix and joint dissipativity-type properties of subsystems and their abstractions. In the…

Optimization and Control · Mathematics 2016-12-30 Majid Zamani , Murat Arcak

Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy. However, existing learning-based solvers often struggle with generalization when faced with changes in problem…

Machine Learning · Computer Science 2023-03-02 Chenguang Wang , Zhouliang Yu , Stephen McAleer , Tianshu Yu , Yaodong Yang

The problem of reversing the compilation process, decompilation, is an important tool in reverse engineering of computer software. Recently, researchers have proposed using techniques from neural machine translation to automate the process…

Cryptography and Security · Computer Science 2022-12-20 Iman Hosseini , Brendan Dolan-Gavitt

Neural abstractions have been recently introduced as formal approximations of complex, nonlinear dynamical models. They comprise a neural ODE and a certified upper bound on the error between the abstract neural network and the concrete…

Logic in Computer Science · Computer Science 2023-10-03 Alec Edwards , Mirco Giacobbe , Alessandro Abate

Abstraction is key to human and artificial intelligence as it allows one to see common structure in otherwise distinct objects or situations and as such it is a key element for generality in AI. Anti-unification (or generalization) is…

Artificial Intelligence · Computer Science 2024-07-23 Christian Antić

In this paper, we delve into the concept of interpretable image enhancement, a technique that enhances image quality by adjusting filter parameters with easily understandable names such as "Exposure" and "Contrast". Unlike using predefined…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Satoshi Kosugi

This paper develops new combinatorial approaches to analyze and compute special set partitions, called complementary set partitions, which are fundamental in the study of generalized cumulants. Moving away from traditional graph-based and…

Statistics Theory · Mathematics 2025-05-20 Elvira Di Nardo , Giuseppe Guarino

Deep Neural Networks (DNNs) deliver impressive performance but their black-box nature limits deployment in high-stakes domains requiring transparency. We introduce Compositional Function Networks (CFNs), a novel framework that builds…

Machine Learning · Computer Science 2025-08-01 Fang Li

Humans have a remarkable ability to rapidly generalize to new tasks that is difficult to reproduce in artificial learning systems. Compositionality has been proposed as a key mechanism supporting generalization in humans, but evidence of…

Neurons and Cognition · Quantitative Biology 2022-09-22 Takuya Ito , Tim Klinger , Douglas H. Schultz , John D. Murray , Michael W. Cole , Mattia Rigotti

Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive…

Machine Learning · Computer Science 2022-02-22 Marco Bertolini , Djork-Arné Clevert , Floriane Montanari

The goal of program synthesis from examples is to find a computer program that is consistent with a given set of input-output examples. Most learning-based approaches try to find a program that satisfies all examples at once. Our work, by…

Machine Learning · Computer Science 2023-06-21 Disha Shrivastava , Hugo Larochelle , Daniel Tarlow

We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs). MI changes the way in which information from difference sources flows and is integrated in the…

Machine Learning · Computer Science 2016-11-15 Yuhuai Wu , Saizheng Zhang , Ying Zhang , Yoshua Bengio , Ruslan Salakhutdinov

Representing visual signals by coordinate-based deep fully-connected networks has been shown advantageous in fitting complex details and solving inverse problems than discrete grid-based representation. However, acquiring such a continuous…

Computer Vision and Pattern Recognition · Computer Science 2022-07-11 Peihao Wang , Zhiwen Fan , Tianlong Chen , Zhangyang Wang