Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Open Access
Neurosymbolic Artificial Intelligence is an open access and transparently peer-reviewed research journal covering a wide range of topics related to neurosymbolic AI.
In the field of artificial intelligence (AI), recent advances in deep learning and big data have resulted in artificial neural networks attaining industrial relevance in a wide range of applications. Neural networks are now the state-of-the-art in language modeling, speech and image classification, sensor data and graph analytics, time series forecasting, and many more tasks requiring the processing of unstructured large data. By contrast, symbolic AI relies on the formalization of knowledge bases and rule-based algorithmic approaches, modeling sound and well-understood reasoning based on expert knowledge. This offers better explanations of AI via knowledge representations that can be inspected to interpret how decisions follow from inputs. However, this is challenged by unstructured large data. Neural and symbolic approaches to AI also provide deeper insights into resolving problems at which they excel. For example, deep learning excels at scene recognition, but it does not achieve state-of-the-art performance at planning, rich deductive reasoning, or complex symbol manipulation.
Neurosymbolic AI is an emerging field of AI aiming to build rich computational AI models, systems and applications by combining neural and symbolic learning and reasoning. It seeks to combine the complementary strengths of neural and symbolic AI while overcoming their respective weaknesses, either in the form of principled integration between both paradigms and forms of representation or in the form of hybrid systems combining neural and symbolic components in one architecture.
Neurosymbolic Artificial Intelligence relies on an open and transparent peer-review process. Submitted manuscripts are posted on the journal's website and are publicly available. In addition to solicited reviews selected by members of the editorial board, public reviews and comments are welcome from any researcher and can be uploaded using the journal’s website. All reviews and responses from the authors are posted on the journal homepage. All involved reviewers and editors will be acknowledged in the final printed version. While we strongly encourage reviewers to participate in the open and transparent review process, it is still possible to submit anonymous reviews.
The journal Neurosymbolic Artificial Intelligence furthermore is a proponent of Open Science Data and requires, whenever possible, that authors provide relevant data and software for evaluation and replication.
