English
Related papers

Related papers: Quantifying The Limits of AI Reasoning: Systematic…

200 papers

In this paper, we review recent approaches for explaining concepts in neural networks. Concepts can act as a natural link between learning and reasoning: once the concepts are identified that a neural learning system uses, one can integrate…

Artificial Intelligence · Computer Science 2024-05-06 Jae Hee Lee , Sergio Lanza , Stefan Wermter

Combining machine learning with logic-based expert systems in order to get the best of both worlds are becoming increasingly popular. However, to what extent machine learning can already learn to reason over rule-based knowledge is still an…

Neural and Evolutionary Computing · Computer Science 2019-03-11 Nuri Cingillioglu , Alessandra Russo

Recent years have witnessed the great success of deep neural networks in many research areas. The fundamental idea behind the design of most neural networks is to learn similarity patterns from data for prediction and inference, which lacks…

Artificial Intelligence · Computer Science 2019-10-22 Shaoyun Shi , Hanxiong Chen , Min Zhang , Yongfeng Zhang

Current advances in Artificial Intelligence and machine learning in general, and deep learning in particular have reached unprecedented impact not only across research communities, but also over popular media channels. However, concerns…

Artificial Intelligence · Computer Science 2019-05-16 Artur d'Avila Garcez , Marco Gori , Luis C. Lamb , Luciano Serafini , Michael Spranger , Son N. Tran

We propose a formal model of reasoning limitations in large neural net models for language, grounded in the depth of their neural architecture. By treating neural networks as linear operators over logic predicate space we show that each…

Artificial Intelligence · Computer Science 2025-07-29 Bill Cochran

Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) by generating natural language (NL) rationales that lead to the final answer. However, it struggles with numerical…

Artificial Intelligence · Computer Science 2025-02-13 Cheryl Li , Tianyuan Xu , Yiwen Guo

Background: Neuro-symbolic methods enhance the reliability of neural network classifiers through logical constraints, but they lack native support for ontologies. Objectives: We aim to develop a neuro-symbolic method that reliably outputs…

Artificial Intelligence · Computer Science 2026-01-22 Nicolas Lazzari , Valentina Presutti , Antonio Vergari

With the advancement of synthetic biology, several new tools have been conceptualized over the years as alternative treatments for current medical procedures. Most of those applications are applied to various chronic diseases. This work…

Field-Programmable Gate Array (FPGA) accelerators have proven successful in handling latency- and resource-critical deep neural network (DNN) inference tasks. Among the most computationally intensive operations in a neural network (NN) is…

Hardware Architecture · Computer Science 2024-12-10 Marta Andronic , George A. Constantinides

Algorithms have been fundamental to recent global technological advances and, in particular, they have been the cornerstone of technical advances in one field rapidly being applied to another. We argue that algorithms possess fundamentally…

Machine Learning · Computer Science 2021-08-09 Petar Veličković , Charles Blundell

Reasoning, the ability to logically draw conclusions from existing knowledge, is a hallmark of human. Together with perception, they constitute the two major themes of artificial intelligence. While deep learning has pushed the limit of…

Artificial Intelligence · Computer Science 2024-10-18 Zhaocheng Zhu

This paper aims to understand how neural networks learn algorithmic reasoning by addressing two questions: How faithful are learned algorithms when they are effective, and why do neural networks fail to learn effective algorithms otherwise?…

Artificial Intelligence · Computer Science 2025-12-09 Lucas Saldyt , Subbarao Kambhampati

Conventional Neural Networks can approximate simple arithmetic operations, but fail to generalize beyond the range of numbers that were seen during training. Neural Arithmetic Units aim to overcome this difficulty, but current arithmetic…

Machine Learning · Computer Science 2020-12-18 Niklas Heim , Tomáš Pevný , Václav Šmídl

Many empirical studies have demonstrated the performance benefits of conditional computation in neural networks, including reduced inference time and power consumption. We study the fundamental limits of neural conditional computation from…

Machine Learning · Computer Science 2023-03-21 Erdem Koyuncu

We investigate the expressive power of neural networks from the point of view of descriptive complexity. We study neural networks that use floating-point numbers and piecewise polynomial activation functions from two perspectives: 1) the…

Computational Complexity · Computer Science 2025-05-12 Veeti Ahvonen , Damian Heiman , Antti Kuusisto

Recent years have witnessed the success of deep neural networks in many research areas. The fundamental idea behind the design of most neural networks is to learn similarity patterns from data for prediction and inference, which lacks the…

Machine Learning · Computer Science 2020-08-24 Shaoyun Shi , Hanxiong Chen , Weizhi Ma , Jiaxin Mao , Min Zhang , Yongfeng Zhang

Boolean circuit is a computational graph that consists of the dynamic directed graph structure and static functionality. The commonly used logic optimization and Boolean matching-based transformation can change the behavior of the Boolean…

Machine Learning · Computer Science 2024-11-19 Liwei Ni , Xinquan Li , Biwei Xie , Huawei Li

Neuro-symbolic methods integrate neural architectures, knowledge representation and reasoning. However, they have been struggling at both dealing with the intrinsic uncertainty of the observations and scaling to real-world applications.…

Artificial Intelligence · Computer Science 2025-01-16 Giuseppe Marra , Michelangelo Diligenti , Francesco Giannini

Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically mapping natural languages to complete formal languages like…

Computation and Language · Computer Science 2024-06-04 Yiming Wang , Zhuosheng Zhang , Pei Zhang , Baosong Yang , Rui Wang

This paper compares three methodological categories of neural reasoning: LLM reasoning, supervised learning-based reasoning, and explicit model-based reasoning. LLMs remain unreliable and struggle with simple decision-making that animals…

Artificial Intelligence · Computer Science 2026-01-05 Tiansi Dong , Henry He , Pietro Liò , Mateja Jamnik