Information Theory (IT) has been used in Machine Learning (ML) from early days of this field. In the last decade, advances in Deep Neural Networks (DNNs) have led to surprising improvements in many applications of ML. The result has been a paradigm shift in the community toward revisiting previous ideas and applications in this new framework. Ideas from IT are no exception. One of the ideas which is being revisited by many researchers in this new era, is Information BOTTLENECK (IB); a formulation of information extraction based on IT. The IB is promising in both analyzing and improving DNNs. The goal of this survey is to review the IB concept and demonstrate its applications in deep learning. The information theoretic nature of IB, makes it also a good candidate in showing the more general concept of how IT can be used in ML. Two important concepts are highlighted in this narrative on the subject, i) the concise and universal view that IT provides on seemingly unrelated methods of ML, demonstrated by explaining how IB relates to minimal sufficient statistics, stochastic gradient descent, and variational auto-encoders, and ii) the common technical mistakes and problems caused by applying ideas from IT, which is discussed by a careful study of some recent methods suffering from them.

Decision-making in competitive situations is a challenge for managers. Identifying the strategic success factors (SSF) for each company and determining the company’s position relative to its competitors due to the SSF are critical, which top managers use for survival in the competitive conditions. The aim of this paper is to create a quantitative method to determine the competitive benchmarking. In this study, average cost of production, company’s brand equity, product quality, marketing and sales capabilities, purchasing capabilities, customer satisfaction, production flexibility, engineering capabilities, technical research capabilities, and the number of R & D projects were identified as critical success factors by the experts of Profile and Pipe Steel Industry. The technique for order preference by similarity to ideal solution was used to determine the positive benchmark (as positive ideal solution) and negative benchmark (as negative ideal solution). Then by considering the budget constraint, binary goal programming model was used to maximize the positive deviation between each rival and the negative benchmark, and to minimize the negative deviation between each rival and the positive benchmark. The results of the proposed model showed that which SSF rival should be considered to reach the positive benchmark.