Generative ai for self-adaptive systems: State of the art and research roadmap

J Li, M Zhang, N Li, D Weyns, Z Jin, K Tei - ACM Transactions on …, 2024 - dl.acm.org
Self-adaptive systems (SASs) are designed to handle changes and uncertainties through a
feedback loop with four core functionalities: monitoring, analyzing, planning, and execution …

Neuro-symbolic learning yielding logical constraints

Z Li, Y Huang, Z Li, Y Yao, J Xu… - Advances in Neural …, 2024 - proceedings.neurips.cc
Neuro-symbolic systems combine the abilities of neural perception and logical reasoning.
However, end-to-end learning of neuro-symbolic systems is still an unsolved challenge. This …

Learning reliable logical rules with SATNet

Z Li, J Guo, Y Jiang, X Si - Advances in Neural Information …, 2023 - proceedings.neurips.cc
Bridging logical reasoning and deep learning is crucial for advanced AI systems. In this
work, we present a new framework that addresses this goal by generating interpretable and …

Concept-centric transformers: Enhancing model interpretability through object-centric concept learning within a shared global workspace

J Hong, KH Park, TP Pavlic - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
Many interpretable AI approaches have been proposed to provide plausible explanations for
a model's decision-making. However, configuring an explainable model that effectively …

Causal language modeling can elicit search and reasoning capabilities on logic puzzles

K Shah, N Dikkala, X Wang, R Panigrahy - arXiv preprint arXiv …, 2024 - arxiv.org
Causal language modeling using the Transformer architecture has yielded remarkable
capabilities in Large Language Models (LLMs) over the last few years. However, the extent …

Learning Iterative Reasoning through Energy Diffusion

Y Du, J Mao, JB Tenenbaum - arXiv preprint arXiv:2406.11179, 2024 - arxiv.org
We introduce iterative reasoning through energy diffusion (IRED), a novel framework for
learning to reason for a variety of tasks by formulating reasoning and decision-making …

Neuro-Symbolic AI Approaches to Enhance Deep Neural Networks with Logical Reasoning and Knowledge Integration

Z Yang - 2023 - search.proquest.com
One of the challenges in Artificial Intelligence (AI) is to integrate fast, automatic, and intuitive
System-1 thinking with slow, deliberate, and logical System-2 thinking. While deep learning …

[PDF][PDF] Multiverse: A Deep Learning 4X4 Sudoku Solver.

C Schendowich, EB Isaac, R Azoulay - ICAART (3), 2024 - scitepress.org
This paper presents a novel deep learning-based approach to solving 4x4 Sudoku puzzles,
by viewing Sudoku as a complex multi-level sequence completion problem. It introduces a …