Learning and Representing Temporal Knowledge in Recurrent Networks

50 citations recorded by the source corpus.

How researchers see this paper

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

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, methodology): “[29],[41],[58], etc. ✓ LTN[42,12] ✓ ✓ ✓ CTLK[8,9], SCTL[5], ✓ NSCA[34] ✓ ✓ ✓ TPRN[32] ✓ ✓ TensorLog[6] ✓ ✓ NLP[57] ✓ ✓ ✓ 𝜕 ILP[14] ✓ ✓ ✓ NTP[39] ✓ ✓ ✓ NLM[13] ✓ ✓ ✓ DeepProbLog[28] ✓ ✓ NSPS[33] ✓ ✓”
Controlling Recurrent Neural Networks by Conceptors (2014, background): “In a field known as neuro-symbolic computation, deduction rules of certain formal logic systems are coded or trained into neural networks [8, 65, 10].”
Logic Tensor Networks (2020, background): “The proliferation of such approaches has prompted Henry Kautz to propose a taxonony for neurosymbolic AI in [34] (also discussed in [16]), including recent work combining neural networks with graphical models and graph neural networks [59, 3, 40], statistical relational learning [20, 56], and even v”
Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks (2018, unknown): “Considerable research has been devoted to the integration of symbolic knowledge and connectionist systems [6], [8], [9], [17], [28]–[32].”
An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks (2017, background): “Indeed, prior work (Borges et al., 2011) has proposed to extract symbolic knowledge from a nonlinear autoregressive models with exogenous (NARX) recurrent model (Lin et al.”