@techreport{Schmitt2021, author = {Schmitt, Ingo}, title = {Generating CQQL conditions from classifying CNNs}, doi = {10.26127/BTUOpen-5550}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:co1-opus4-55503}, year = {2021}, abstract = {Convolutional neural networks are often successfully used for classification problems. Usually, a huge number of weights need to be learnt by use of training data. However, the learnt weights give no insight how the cnn really works. Thus, a cnn can be seen as a black box solution. In our approach we develop a method to generate a commuting quantum query language (cqql) condition from a sample derived from a given cnn or from training input. CQQL is inspired by quantum logic and its conditions obey the rules of Boolean algebra. The evaluation of a cqql condition provides values from the unit interval [0; 1] and establishes therefore an elegant bridge between logic and a cnn. The underlying assumption is that a condition (a logic expression) gives much more understanding than pure cnn weights. Furthermore, the rich theory of Boolean algebra can be used for manipulating logic expressions. After extracting a cqql condition from a cnn or its training data we can use logic as a way to predict classes alternatively to a cnn.}, subject = {CQQL; Quantum Logic; CNN; CQQL; Quantenlogik; CNN; Erkl{\"a}rbarkeit; Zellulares neuronales Netzwerk; Abfragesprache; Quantenlogik}, language = {en} }