Neural networks are state-of-the-art classification approaches but are generally difficult to interpret. This issue can be partly alleviated by constructing a precise decision process within the neural network. In this work, a network architecture, denoted as Classification-By-Components network (CBC), is proposed.

Neural networks are state-of-the-art classification approaches but are generally difficult to interpret. This issue can be partly alleviated by constructing a precise decision process within the neural network. In this work, a network architecture, denoted as Classification-By-Components network (CBC), is proposed. It is restricted to follow an intuitive reasoning based decision process inspired by Biederman's recognition-by-components theory from cognitive psychology. The network is trained to learn and detect generic components that characterize objects.

Originality - this research is similar to prototype-based learning of neural networks, but it is the first to propose learning and detecting generic components that characterize object using three different types of reasoning (positive, negative and indefinite). Clarity - the paper is hard to read and follow. There are large chunks of text with no figures or equations to illustrate the concepts. In the supplementary material they provide a lot more information which was left out of the main paper. It does feel like the paper is not self-sufficient, as many important steps are only brushed over, such as the training procedure and how to generate the interpretations.

The paper proposes an interesting probabilistic reasoning process that considers the presence or absence of various components (that are indicative of several properties of an instance) and combines them together as (potentially interpretable) evidence for its final classification. The idea seems to us novel and interesting. Multiple experiments are provided to support the approach. The paper is also well-written and clear.

Neural networks are state-of-the-art classification approaches but are generally difficult to interpret. This issue can be partly alleviated by constructing a precise decision process within the neural network. In this work, a network architecture, denoted as Classification-By-Components network (CBC), is proposed. It is restricted to follow an intuitive reasoning based decision process inspired by Biederman's recognition-by-components theory from cognitive psychology. The network is trained to learn and detect generic components that characterize objects.

Neural networks are state-of-the-art classification approaches but are generally difficult to interpret. This issue can be partly alleviated by constructing a precise decision process within the neural network. In this work, a network architecture, denoted as Classification-By-Components network (CBC), is proposed. It is restricted to follow an intuitive reasoning based decision process inspired by Biederman's recognition-by-components theory from cognitive psychology. The network is trained to learn and detect generic components that characterize objects.