Neural-Symbolic Learning Systems

By M. D. P. Artur S. d’Avila Garcez MEng, BA MSc PhD Krysia B. Broda BSc, F. F. Dov M. Gabbay FRSC. 2002

Citations in the corpus

• Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning (2017, neutral): “These neural-symbolic systems (Garcez et al., 2012) include early examples such as KBANN (Towell et al., 1990) that construct network architectures from given rules to perform reasoning.”
• Neurosymbolic AI: the 3rd wave (2020, methodology): “…computing has sought to offer a principled way of studying learning and reasoning by establishing provable correspondences between neural models and logical representations (d’Avila Garcez et al. 2002, 2009, 2015; Lamb et al. 2020), which will be discussed in more detail later in the paper.”
• Fast relational learning using bottom clause propositionalization with artificial neural networks (2013, unknown): “Systems that combine symbolic computation with neural networks are called neural-symbolic systems (Garcez et al., 2002).”