Augmenting deep neural networks with symbolic knowledge: Towards trustworthy and interpretable AI for education

• URL: http://arxiv.org/abs/2311.00393v1
• Date: Wed, 1 Nov 2023 09:38:56 GMT
• Title: Augmenting deep neural networks with symbolic knowledge: Towards trustworthy and interpretable AI for education
• Authors: Danial Hooshyar, Roger Azevedo, Yeongwook Yang
• Abstract summary: This research argues that the neural-symbolic family of AI has the potential to address the named challenges. It adapts a neural-symbolic AI framework and accordingly develops an approach called NSAI, that injects and extracts educational knowledge into and from deep neural networks. Our findings reveal that the NSAI approach has better generalizability compared to deep neural networks trained merely on training data.
• Score: 3.627954884906034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Artificial neural networks (ANNs) have shown to be amongst the most important artificial intelligence (AI) techniques in educational applications, providing adaptive educational services. However, their educational potential is limited in practice due to three major challenges: i) difficulty in incorporating symbolic educational knowledge (e.g., causal relationships, and practitioners' knowledge) in their development, ii) learning and reflecting biases, and iii) lack of interpretability. Given the high-risk nature of education, the integration of educational knowledge into ANNs becomes crucial for developing AI applications that adhere to essential educational restrictions, and provide interpretability over the predictions. This research argues that the neural-symbolic family of AI has the potential to address the named challenges. To this end, it adapts a neural-symbolic AI framework and accordingly develops an approach called NSAI, that injects and extracts educational knowledge into and from deep neural networks, for modelling learners computational thinking. Our findings reveal that the NSAI approach has better generalizability compared to deep neural networks trained merely on training data, as well as training data augmented by SMOTE and autoencoder methods. More importantly, unlike the other models, the NSAI approach prioritises robust representations that capture causal relationships between input features and output labels, ensuring safety in learning to avoid spurious correlations and control biases in training data. Furthermore, the NSAI approach enables the extraction of rules from the learned network, facilitating interpretation and reasoning about the path to predictions, as well as refining the initial educational knowledge. These findings imply that neural-symbolic AI can overcome the limitations of ANNs in education, enabling trustworthy and interpretable applications.

Related papers

• Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents [55.63497537202751]
  Article explores the convergence of connectionist and symbolic artificial intelligence (AI) Traditionally, connectionist AI focuses on neural networks, while symbolic AI emphasizes symbolic representation and logic. Recent advancements in large language models (LLMs) highlight the potential of connectionist architectures in handling human language as a form of symbols.
  arXiv  Detail & Related papers  (2024-07-11T14:00:53Z)
• Enhancing learning in spiking neural networks through neuronal heterogeneity and neuromodulatory signaling [52.06722364186432]
  We propose a biologically-informed framework for enhancing artificial neural networks (ANNs) Our proposed dual-framework approach highlights the potential of spiking neural networks (SNNs) for emulating diverse spiking behaviors. We outline how the proposed approach integrates brain-inspired compartmental models and task-driven SNNs, bioinspiration and complexity.
  arXiv  Detail & Related papers  (2024-07-05T14:11:28Z)
• A Synergistic Approach In Network Intrusion Detection By Neurosymbolic AI [6.315966022962632]
  This paper explores the potential of incorporating Neurosymbolic Artificial Intelligence (NSAI) into Network Intrusion Detection Systems (NIDS) NSAI combines deep learning's data-driven strengths with symbolic AI's logical reasoning to tackle the dynamic challenges in cybersecurity. The inclusion of NSAI in NIDS marks potential advancements in both the detection and interpretation of intricate network threats.
  arXiv  Detail & Related papers  (2024-06-03T02:24:01Z)
• Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI [33.0761784111292]
  Neuro-symbolic AI emerges as a promising paradigm to enhance interpretability, robustness, and trustworthiness. Recent NSAI systems have demonstrated great potential in collaborative human-AI scenarios with reasoning and cognitive capabilities.
  arXiv  Detail & Related papers  (2024-01-02T05:00:54Z)
• A Novel Neural-symbolic System under Statistical Relational Learning [50.747658038910565]
  We propose a general bi-level probabilistic graphical reasoning framework called GBPGR. In GBPGR, the results of symbolic reasoning are utilized to refine and correct the predictions made by the deep learning models. Our approach achieves high performance and exhibits effective generalization in both transductive and inductive tasks.
  arXiv  Detail & Related papers  (2023-09-16T09:15:37Z)
• Brain-Inspired Computational Intelligence via Predictive Coding [89.6335791546526]
  Predictive coding (PC) has shown promising performance in machine intelligence tasks. PC can model information processing in different brain areas, can be used in cognitive control and robotics.
  arXiv  Detail & Related papers  (2023-08-15T16:37:16Z)
• Knowledge-enhanced Neuro-Symbolic AI for Cybersecurity and Privacy [3.425341633647625]
  Neuro-Symbolic Artificial Intelligence combines the subsymbolic strengths of neural networks and explicit, symbolic knowledge graphs. This article describes how applications in cybersecurity and privacy, two most demanding domains, can benefit from Neuro-Symbolic AI.
  arXiv  Detail & Related papers  (2023-07-25T01:29:34Z)
• Neuro-Symbolic Learning of Answer Set Programs from Raw Data [54.56905063752427]
  Neuro-Symbolic AI aims to combine interpretability of symbolic techniques with the ability of deep learning to learn from raw data. We introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a general neural network to extract latent concepts from raw data. NSIL learns expressive knowledge, solves computationally complex problems, and achieves state-of-the-art performance in terms of accuracy and data efficiency.
  arXiv  Detail & Related papers  (2022-05-25T12:41:59Z)
• Neurosymbolic AI: The 3rd Wave [1.14219428942199]
  Concerns about trust, safety, interpretability and accountability of AI were raised by influential thinkers. Many have identified the need for well-founded knowledge representation and reasoning to be integrated with deep learning. Neural-symbolic computing has been an active area of research seeking to bring together robust learning in neural networks with reasoning and explainability.
  arXiv  Detail & Related papers  (2020-12-10T18:31:38Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.