Deep neural networks (DNNs) detect patterns in data and have shown versatility and strong performance in many computer vision applications. However, DNNs alone are susceptible to obvious mistakes that violate simple, common sense concepts and are limited in their ability to use explicit knowledge to guide their search and decision making. While overall DNN performance metrics may be good, these obvious errors, coupled with a lack of explainability, have prevented widespread adoption for crucial tasks such as medical image analysis. The purpose of this paper is to introduce SimpleMind, an open-source software framework for Cognitive AI focused on medical image understanding. It allows creation of a knowledge base that describes expected characteristics and relationships between image objects in an intuitive human-readable form. The SimpleMind framework brings thinking to DNNs by: (1) providing methods for reasoning with the knowledge base about image content, such as spatial inferencing and conditional reasoning to check DNN outputs; (2) applying process knowledge, in the form of general-purpose software agents, that are chained together to accomplish image preprocessing, DNN prediction, and result post-processing, and (3) performing automatic co-optimization of all knowledge base parameters to adapt agents to specific problems. SimpleMind enables reasoning on multiple detected objects to ensure consistency, providing cross checking between DNN outputs. This machine reasoning improves the reliability and trustworthiness of DNNs through an interpretable model and explainable decisions. Example applications are provided that demonstrate how SimpleMind supports and improves deep neural networks by embedding them within a Cognitive AI framework.

Besides the typical applications of recommender systems in B2C scenarios such as movie or shopping platforms, there is a rising interest in transforming the human-driven advice provided e.g. in consultancy via the use of recommender systems. We explore the special characteristics of such knowledge-based B2B services and propose a process that allows to incorporate recommender systems into them. We suggest and compare several recommender techniques that allow to incorporate the necessary contextual knowledge (e.g. company demographics). These techniques are evaluated in isolation on a test set of business intelligence consultancy cases. We then identify the respective strengths of the different techniques and propose a new hybridisation strategy to combine these strengths. Our results show that the hybridisation leads to a substantial performance improvement over the individual methods.

The paper addresses aggregation issues for composite (modular) solutions. A systemic view point is suggested for various aggregation problems. Several solution structures are considered: sets, set morphologies, trees, etc. Mainly, the aggregation approach is targeted to set morphologies. The aggregation problems are based on basic structures as substructure, superstructure, median/consensus, and extended median/consensus. In the last case, preliminary structure is built (e.g., substructure, median/consensus) and addition of solution elements is considered while taking into account profit of the additional elements and total resource constraint. Four aggregation strategies are examined: (i) extension strategy (designing a substructure of initial solutions as "system kernel" and extension of the substructure by additional elements); (ii) compression strategy (designing a superstructure of initial solutions and deletion of some its elements); (iii) combined strategy; and (iv) new design strategy to build a new solution over an extended domain of solution elements. Numerical real-world examples (e.g., telemetry system, communication protocol, student plan, security system, Web-based information system, investment, educational courses) illustrate the suggested aggregation approach.