concept

Convolutional Neural Networks

Also known as: CNN

Facts (11)

Sources

A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Springer Dec 9, 2025 4 facts

claimIn neuro-symbolic visual reasoning tasks, convolutional neural networks (CNNs) detect objects and spatial relations, while symbolic reasoning modules ensure interpretations adhere to commonsense physical laws, such as the rule that a cup cannot float above a table without support.

referenceRobotics and autonomous systems often utilize a two-tier neuro-symbolic architecture where the first tier uses neural perception modules, such as convolutional neural networks, vision transformers, or event-based sensors, to segment scenes and instantiate logical atoms, while the second tier uses a symbolic task and motion planner to synthesize policies and enforce safety invariants.

claimConvolutional neural networks integrated with attention mechanisms have been applied to magnetic resonance imaging (MRI) for brain tumor classification, providing accurate localization and interpretable activation maps.

referenceRasheed et al. (2024) published a study in Bioengineering titled 'Integrating convolutional neural networks with attention mechanisms for magnetic resonance imaging-based classification of brain tumors,' which explores the application of neural networks in medical imaging.

Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org arXiv 2 facts

claimNeural relation extraction focuses on investigating neural network architectures, such as recurrent neural networks, convolutional neural networks, and LSTMs, rather than relying on hand-crafted features.

referenceT.H. Nguyen and R. Grishman published 'Relation Extraction: Perspective from Convolutional Neural Networks' in the proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing (VS@NAACL-HLT 2015) in Denver, Colorado, USA, in June 2015.

Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org arXiv Feb 16, 2025 1 fact

referenceRaja Ayyanar, George Koomullil, and Hariharan Ramasangu performed causal relation classification using convolutional neural networks and grammar tags, presented at the 2019 IEEE 16th India Council International Conference (INDICON).

Knowledge Enhanced Industrial Question-Answering Using Large ... engineering.org.cn Ronghui Liu, Hao Ren, Haojie Ren, Wu Rui, Wei Cui, Xiaojun Liang, Chunhua Yang, Weihua Gui 1 fact

referenceY. Kim published the paper 'Convolutional neural networks for sentence classification' in the Association for Computational Linguistics proceedings in 2014, pages 1746-1751, in Doha, Qatar.

Efficient Knowledge Graph Construction and Retrieval from ... - arXiv arxiv.org arXiv Aug 7, 2025 1 fact

referenceFarhad Nooralahzadeh, Lilja Øvrelid, and Jan Tore Lønning published 'Sirius-ltg-uio at semeval-2018 task 7: Convolutional neural networks with shortest dependency paths for semantic relation extraction and classification in scientific papers' in 2018.

Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS 1 fact

claimMulti-task representation learning outperforms single-task representation learning in scenarios involving over-parameterized two-layer convolutional neural networks trained by gradient descent.

The construction and refined extraction techniques of knowledge ... nature.com Nature Feb 10, 2026 1 fact

claimConvolutional Neural Networks (CNNs) improve Relation Extraction (RE) classification by extracting local features, while distant supervision enables automatic labeling but introduces noise.