Aragam, Bryon; Ravikumar, Pradeep
(, Frontiers in Artificial Intelligence and Applications)
Hitzler, P; Sarker, MK; Eberhart, A
(Ed.)
We describe a novel neuro-symbolic model architecture we term "neuro-causal models," that uses a synthesis of deep generative models and causal graphical models to automatically infer higher level symbolic information from lower level "raw features", while also allowing for rich relationships among the symbolic variables.
Alers-Valentín, Hilton; Fong, Sandiway; Vega-Riveros, Jose F
(, SCITEPRESS - Science and Technology Publications)
To overcome the limitations of prevailing NLP methods, a Hybrid-Architecture Symbolic Parser and Neural Lexicon system is proposed to detect structural ambiguity by producing as many syntactic representations as there are interpretations for an utterance. HASPNeL comprises a symbolic AI, feature-unification parser, a lexicon generated using manual classification and machine learning, and a neural network encoder which tags each lexical item in a synthetic corpus and estimates likelihoods for each utterance’s interpretation with respect to the corpus. Language variation is accounted for by lexical adjustments in feature specifications and minimal parameter settings. Contrary to pure probabilistic system, HASPNeL’s neuro-symbolic architecture will perform grammaticality judgements of utterances that do not correspond to rankings of probabilistic systems; have a greater degree of system stability as it is not susceptible to perturbations in the training data; detect lexical and structural ambiguity by producing all possible grammatical representations regardless of their presence in the training data; eliminate the effects of diminishing returns, as it does not require massive amounts of annotated data, unavailable for underrepresented languages; avoid overparameterization and potential overfitting; test current syntactic theory by implementing a Minimalist grammar formalism; and model human language competence by satisfying conditions of learnability, evolvability, and universality.
Najafi, Deniz, Barkam, Hamza Errahmouni, Morsali, Mehrdad, Jeong, SungHeon, Das, Tamoghno, Roohi, Arman, Nikdast, Mahdi, Imani, Mohsen, and Angizi, Shaahin. Neuro-Photonix: Enabling Near-Sensor Neuro-Symbolic AI Computing on Silicon Photonics Substrate. Retrieved from https://par.nsf.gov/biblio/10586590. IEEE Transactions on Circuits and Systems for Artificial Intelligence . Web. doi:10.1109/TCASAI.2025.3537968.
Najafi, Deniz, Barkam, Hamza Errahmouni, Morsali, Mehrdad, Jeong, SungHeon, Das, Tamoghno, Roohi, Arman, Nikdast, Mahdi, Imani, Mohsen, and Angizi, Shaahin.
"Neuro-Photonix: Enabling Near-Sensor Neuro-Symbolic AI Computing on Silicon Photonics Substrate". IEEE Transactions on Circuits and Systems for Artificial Intelligence (). Country unknown/Code not available: IEEE. https://doi.org/10.1109/TCASAI.2025.3537968.https://par.nsf.gov/biblio/10586590.
@article{osti_10586590,
place = {Country unknown/Code not available},
title = {Neuro-Photonix: Enabling Near-Sensor Neuro-Symbolic AI Computing on Silicon Photonics Substrate},
url = {https://par.nsf.gov/biblio/10586590},
DOI = {10.1109/TCASAI.2025.3537968},
abstractNote = {},
journal = {IEEE Transactions on Circuits and Systems for Artificial Intelligence},
publisher = {IEEE},
author = {Najafi, Deniz and Barkam, Hamza Errahmouni and Morsali, Mehrdad and Jeong, SungHeon and Das, Tamoghno and Roohi, Arman and Nikdast, Mahdi and Imani, Mohsen and Angizi, Shaahin},
}
Warning: Leaving National Science Foundation Website
You are now leaving the National Science Foundation website to go to a non-government website.
Website:
NSF takes no responsibility for and exercises no control over the views expressed or the accuracy of
the information contained on this site. Also be aware that NSF's privacy policy does not apply to this site.
An official website of the United States government
