Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems
A Oltramari - Proceedings of the AAAI Symposium Series, 2023 - ojs.aaai.org
High-level reasoning can be defined as the capability to generalize over knowledge
acquired via experience, and to exhibit robust behavior in novel situations. Such form of …
acquired via experience, and to exhibit robust behavior in novel situations. Such form of …
Deep deductive reasoning is a hard deep learning problem
Abstract Deep Deductive Reasoning refers to the training and then executing of deep
learning systems to perform deductive reasoning in the sense of formal, mathematical logic …
learning systems to perform deductive reasoning in the sense of formal, mathematical logic …
[PDF][PDF] Cognitive Neuro-Symbolic Reasoning Systems.
A Oltramari - AAAI Spring Symposium: MAKE, 2023 - ceur-ws.org
Abstract Knowledge-infusion methods are key to enhance neural models and improve their
performance, but they are not sufficient to enable high-level reasoning, which is typically …
performance, but they are not sufficient to enable high-level reasoning, which is typically …
[PDF][PDF] Generalizable Neuro-Symbolic Systems for Commonsense Question Answering
We illustrate how the combination of data-driven algorithms and symbolic knowledge is
necessary to enable domain generalizability and robustness in downstream tasks. Our work …
necessary to enable domain generalizability and robustness in downstream tasks. Our work …
[PDF][PDF] A Path Towards High-Level Reasoning Through Cognitive Neuro-Symbolic Systems
A Oltramari - neurosymbolic-ai-journal.com
Knowledge-infusion methods are key to enhance neural models and improve their
performance in downstream tasks, but they are not sufficient to enable high-level reasoning …
performance in downstream tasks, but they are not sufficient to enable high-level reasoning …