📘 This week:
Neuro-Symbolic AI brings together the statistical nature of machine learning with the formal reasoning capabilities of symbolic AI. It seeks to offer a balanced approach to contemporary AI technologies, by combining the ability to learn from data, with the capacity to reason upon knowledge acquired from an environment. The main criticism of neural machine learning lies in its lack of explainability and semantics, which are key requirements in safety-critical applications, yet inherent strengths of logic-based methods. Recently, several corporations have publicly announced products and technologies grounded in Neuro-Symbolic AI methodologies. This talk provided a concise review of the foundations, frameworks and tools underlying Neuro-Symbolic AI, along with illustrative applications. It concludes by highlighting current trends and research directions in the field.
📝 Suggested paper:
A Garcez, LC Lamb:
Neurosymbolic AI: the 3rd wave. Artif. Intell. Review 56(11):12387-12406 (2023)
https://link.springer.com/article/10.1007/s10462-023-10448-w
Top comments (0)