Tensor Networks : Deep Learning and Logical Reasoning from Data and Knowledge ⋆

By Luciano Serafini, A.S. d'Avila Garcez. 2016

Subfields: Model Architectures, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

In Graph Learning

Citations in the corpus

The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020, background): “Logic tensor networks (Serafini & Garcez, 2016) aim to implement a formal logic in deep tensor neural networks.”
End-to-end Differentiable Proving (2017, background): “rn subsymbolic vector representations from training facts in aKB(e.g., SHRUTI [42], Neural Prolog [43], CLIP++ [44], Lifted Relational Neural Networks [45], and TensorLog [46]). Logic Tensor Networks [47] are in spirit similar toNTPs, but need to fully ground ﬁrst-order logic rules. However, they su”
Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies (2021, background): “Seraﬁni and d’Avila Garcez (2016) proposed logic tensor networks, a uniform framework for integrating automatic learning and reasoning.”
Logic Tensor Networks (2020, methodology): “The approach adopted by Lyrics [47] is analogous to the first version of LTN [62].”
Emerging Technology and Business Model Innovation: The Case of Artificial Intelligence (2019, methodology): “AI has been fostering business model innovation across industries including technology/media, consumer products, financial services, health care, industrial, energy, public sector, and so on [32].”
Siamese recurrent networks learn first-order logic reasoning and exhibit zero-shot compositional generalization (2019, background): “Moreover, entailment recognition models are often endowed with functionality reflecting pre-established linguistic or semantic regularities of the data (Bankova et al., 2016; Serafini and Garcez, 2016; Sadrzadeh et al., 2018).”
On a Convex Logic Fragment for Learning and Reasoning (2018, background): “cal constraints and like other authors do [22], [24], we decided to focus on Łukasiewicz logic.”
Logical Rule Induction and Theory Learning Using Neural Theorem Proving (2018, background): “In (Seraﬁni and Garcez 2016) they introduce Logic Tensor Networks (LTN) and Real Logic whose semantics grounds the terms, atoms and clauses of the language as continuous functions.”
Deep learning for noise-tolerant RDFS reasoning (2019, background): “Logic Tensor Networks [81] allow the definition of logical constraints to improve the KGC.”