An application of explainable artificial intelligence on medical data is presented. There is an increasing demand in machine learning literature for such explainable models in health-related applications. This work aims to generate explanations on how a Convolutional Neural Network (CNN) detects tumor tissue in patches extracted from histology whole slide images. This is achieved using the “locally-interpretable model-agnostic explanations” methodology. Two publicly-available convolutional neural networks trained on the Patch Camelyon Benchmark are analyzed. Three common segmentation algorithms are compared for superpixel generation, and a fourth simpler parameter-free segmentation algorithm is proposed. The main characteristics of the explanations are discussed, as well as the key patterns identified in true positive predictions. The results are compared to medical annotations and literature and suggest that the CNN predictions follow at least some aspects of human expert knowledge.

Well placement optimization is a very challenging problem due to the large number of decision variables involved and the nonlinearity of the reservoir response as well as of the well placement constraints. Over the years, a lot of research has been done on this problem, most of which using optimization routines coupled to reservoir simulation models. Despite all this research, there is still a lack of robust computer-aided optimization tools ready to be applied by asset teams in real field development projects. This paper describes the implementation of a tool, based on a Genetic Algorithm, for the simultaneous optimization of number, location and trajectory of producer and injector wells. The developed software is the result of a two-year project focused on a robust implementation of a computer-aided optimization tool to deal with realistic well placement problems with arbitrary well trajectories, complex model grids and linear and nonlinear constraints. The developed optimization tool uses a commercial reservoir simulator as the evaluation function without using proxies to substitute the full numerical model. Due to the large size of the problem, in some cases involving more than 100 decision variables, the optimization process may require thousands of reservoir simulations. Such a task has become feasible through a distributed computing environment running multiple simulations at the same time. The implementation uses a technique called Genocop III – Genetic Algorithm for Numerical Optimization of Constrained Problems – to deal with well placement constraints. Such constraints include grid size, maximum length of wells, minimum distance between wells, inactive grid cells and user-defined regions of the model, with non-uniform shape, where the optimization routine is not supposed to place wells. The optimization process was applied to three full-field reservoir models based on real cases. It increased the net present values and the oil recovery factors obtained by well placement scenarios previously proposed by reservoir engineers. The process was also applied to a synthetic case, based on outcrop data, to analyze the impact of using reservoir quality maps to generate an initial well placement scenario for the optimization routine without using an engineer-defined configuration.

This paper introduces the Inverted Hierarchical Neuro-Fuzzy BSP System (HNFB/sup -1/), a new neuro-fuzzy model that has been specifically created for record classification and rule extraction in databases. The HNFB/sup -1/ is based on the Hierarchical Neuro-Fuzzy Binary Space Partitioning Model (HNFB), which embodies a recursive partitioning of the input space, is able to automatically generate its own structure, and allows a greater number of inputs. The new HNFB/sup -1/ allows the extraction of knowledge in the form of interpretable fuzzy rules expressed by the following: If x is A and y is B, then input pattern belongs to class Z. For the process of rule extraction in the HNFB/sup -1/ model, two fuzzy evaluation measures were defined: 1) fuzzy accuracy and 2) fuzzy coverage. The HNFB/sup -1/ has been evaluated with different benchmark databases for the classification task: Iris Dataset, Wine Data, Pima Indians Diabetes Database, Bupa Liver Disorders, and Heart Disease. When compared with several other pattern classification models and algorithms, the HNFB/sup -1/ model has shown similar or better classification performance. Nevertheless, its performance in terms of processing time is remarkable. The HNFB/sup -1/ converged in less than one minute for all the databases described in the case study.

An introduction to neural networks and neural information processing is provided. Neurocomputers are discussed, focusing on how their design exploits the architectural properties of VLSI circuits. General-purpose and special-purpose neurocomputer developments throughout the world are examined. As illustration, and to put European developments in perspective, some of the important projects in the United States and Japan are described. European research is then discussed in greater detail.<>