Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature

Abstract

The need for neural-symbolic integration becomes apparent as more complex problems are tackled, and they go beyond limited domain tasks such as classification. In this sense, understanding the state of the art of hybrid technologies based on Deep Learning and augmented with logic based systems, is of utmost importance. As a consequence, we seek to understand and represent the current state of these technologies that are highly used in intelligent systems engineering.This work aims to provide a comprehensive view of the solutions available in the literature, within the field of applied Artificial Intelligence (AI), using technologies based on AI techniques that integrate symbolic and non-symbolic logic (in particular artificial neural networks), making them the subject of a systematic literature review (SLR). The resulting technologies are discussed and evaluated from both perspectives: symbolic and non-symbolic AI.In this work, we use the PICOC & Limits method to define the research questions and analyze the results.Out of a total of 65 candidate studies found, 24 articles (37%) relevant to this study were selected. Each study also focuses on different application domains. Conclusion: Through the analysis of the selected works throughout this review, we have seen different combinations of logical systems with some form of neural network and, although we have not found a clear architectural pattern, efforts to find a model of general purpose combining both worlds drive trends and research efforts.

Raman Spectroscopy System for Water Pollution Control based on Artificial Neural Network

“…In this paper, raman spectroscopy (RS) was used for water quality anomaly detection and pollutant class differentiation [11][12], and the main work on water quality characterization based on multispectral methods included the following three aspects.…”

Water Pollution Prevention and Prediction Based on Grey BP Neural Network Model

“…In the specific prediction of WP, the construction of neural networks requires a large amount of test data, but the problem is the reduction of information that cannot be avoided by traditional neural networks [7]. To address this problem, the approach used in this paper is to front a BPNN model with a grey system, a method that reduces significant information and which has the advantage of simplifying the input values in order to reduce the time BP takes to train the neural network in front and to improve the ultimate accuracy of the training [8][9].…”

Research the Effect of Oxidation Catalytic Converter on Reducing Diesel Engine Particulate Emission Based on Artificial Intelligence

“…(2) Air intake system: The air intake system consists of the compressor inlet, the upstream air duct and contains a simple model of the airbox. At the inlet and outlet of the airbox, conical orifice connections are used to simulate a smooth transition [11].…”