Generating CQQL Conditions from Classifying CNNs
- Convolutional neural networks are often successfully used for clas- si cation 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. The query language cqql is inspired by quantum logic and its conditions obey the rules of a 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 classesConvolutional neural networks are often successfully used for clas- si cation 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. The query language cqql is inspired by quantum logic and its conditions obey the rules of a 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.…
Author: | Ingo SchmittORCiDGND |
---|---|
URN: | urn:nbn:de:kobv:co1-opus4-55503 |
DOI: | https://doi.org/10.26127/BTUOpen-5550 |
ISSN: | 1437-7969 |
Place of publication: | Cottbus |
Document Type: | Report |
Language: | English |
Year of publication: | 2021 |
Tag: | Abfragesprache; CNN; Erklärbarkeit; Quantenlogik; Zellulares neuronales Netzwerk CNN; CQQL; Quantum Logic |
Number of pages: | 15 |
Series ; volume number: | Computer science reports / Institut für Informatik (2021, 1) |
Faculty/Chair: | Fakultät 1 MINT - Mathematik, Informatik, Physik, Elektro- und Informationstechnik / FG Datenbank- und Informationssysteme |