1,721,125 research outputs found
Preface – Proceedings of the 37th Italian Conference on Computational Logic (CILC 2022)
No full textPreface of the Proceedings of the 37th Italian Conference on Computational Logic (CILC 2022
KINS: Knowledge Injection via Network Structuring
Full text linkWe propose a novel method to inject symbolic knowledge in form of Datalog formulæ into neural networks (NN), called KINS (Knowledge Injection via Network Structuring). The idea behind our method is to extend NN internal structure with ad-hoc layers built out the injected symbolic knowledge. KINS does not constrain NN to any specific architecture, neither requires logic formulæ to be ground. Moreover, it is robust w.r.t. both lack of data and imperfect/incomplete knowledge. Experiments are reported to demonstrate the potential of KINS
Preface – AI&IoT 2019
No full textThe Internet of Things (IoT) is expected to reach its full potential through actually intelligent and autonomous cyber-physical devices and systems. Along this line, Artificial Intelligence (AI) is likely to be the best source of resources – such as algorithms, technologies, methodologies, and paradigms – enabling the development of next-generation “smart” devices and systems. In fact, the “IoT-AI” combination let us envision a cyber- physical scenario where devices compute while opportunistically interacting with each other, with human users, and with their surrounding environments in a dynamic, adaptive, and cognitive way. It is reasonable to expect that great benefits for the IoT can emerge by combining the whole spectrum of AI techniques with the various approaches used in the IoT to distribute data and computation and to exploit the interaction between multiple devices. For this reason, the AI&IoT Workshop aims to explore not only the adaptation of existing AI techniques to the IoT context, but also new specific and original approaches for the development of intelligent IoT ecosystems as well as new business models and relevant experiences from successful smart applications
Graph Neural Networks as the Copula Mundi between Logic and Machine Learning: A Roadmap
Full text linkCombining machine learning (ML) and computational logic (CL) is hard, mostly because of the inherently- different ways they use to represent knowledge. In fact, while ML relies on fixed-size numeric repre- sentations leveraging on vectors, matrices, or tensors of real numbers, CL relies on logic terms and clauses—which are unlimited in size and structure.
Graph neural networks (GNN) are a novelty in the ML world introduced for dealing with graph- structured data in a sub-symbolic way. In other words, GNN pave the way towards the application of ML to logic clauses and knowledge bases. However, there are several ways to encode logic knowledge into graphs: which is the best one heavily depends on the specific task at hand.
Accordingly, in this paper, we (i) elicit a number of problems from the field of CL that may benefit from many graph-related problems where GNN has been proved effective; (ii) exemplify the application of GNN to logic theories via an end-to-end toy example, to demonstrate the many intricacies hidden behind the technique; (iii) discuss the possible future directions of the application of GNN to CL in general, pointing out opportunities and open issues
On the Design of PSyKE: A Platform for Symbolic Knowledge Extraction
Full text linkA common practice in modern explainable AI is to post-hoc explain black-box machine learning (ML) predictors – such as neural networks – by extracting symbolic knowledge out of them, in the form of either rule lists or decision trees. By acting as a surrogate model, the extracted knowledge aims at revealing the inner working of the black box, thus enabling its inspection, representation, and explanation.
Various knowledge-extraction algorithms have been presented in the literature so far. Unfortunately, running implementations of most of them are currently either proof of concepts or unavailable. In any case, a unified, coherent software framework supporting them all – as well as their interchange, comparison, and exploitation in arbitrary ML workflows – is currently missing.
Accordingly, in this paper we present the design of PSyKE, a platform providing general-purpose support to symbolic knowledge extraction from different sorts of black-box predictors via many extraction algorithms. Notably, PSyKE targets the extraction of symbolic knowledge in logic form, making it possible to extract first-order logic clauses as output. The extracted knowledge is thus both machine- and human- interpretable, and it can be used as a starting point for further symbolic processing—e.g. automated reasoning
CILC 2022 – Italian Conference on Computational Logic
No full textProceedings of the 37th Italian Conference on Computational Logic (CILC 2022
On the integration of symbolic and sub-symbolic techniques for XAI: A survey
Full text linkThe more intelligent systems based on sub-symbolic techniques pervade our everyday lives, the less human can understand them. This is why symbolic approaches are getting more and more attention in the general effort to make AI interpretable, explainable, and trustable. Understanding the current state of the art of AI techniques integrating symbolic and sub-symbolic approaches is then of paramount importance, nowadays—in particular in the XAI perspective. This is why this paper provides an overview of the main symbolic/sub-symbolic integration techniques, focussing in particular on those targeting explainable AI systems
Knowledge injection of Datalog rules via Neural Network Structuring with KINS
No full textWe propose a novel method to inject symbolic knowledge in form of Datalog formulæ into neural networks (NN), called Knowledge Injection via Network Structuring (KINS). The idea behind our method is to extend NN internal structure with ad-hoc layers built out of the injected symbolic knowledge. KINS does not constrain NN to any specific architecture, neither requires logic formulæ to be ground. Moreover, it is robust w.r.t. both lack of data and imperfect/incomplete knowledge. Experiments are reported, involving multiple datasets and predictor types, to demonstrate how KINS can significantly improve the predictive performance of the neural networks it is applied to
- …
