The Art of Seeing and Painting

The human urge to represent the three-dimensional world using two-dimensional pictorial representations dates back at least to Paleolithic times. Artists from ancient to modern times have struggled to understand how a few contours or color patches on a flat surface can induce mental representations of a three-dimensional scene. This article summarizes some of the recent breakthroughs in scientifically understanding how the brain sees that shed light on these struggles. These breakthroughs illustrate how various artists have intuitively understand paradoxical properties about how the brain sees, and have used that understanding to create great art. These paradoxical properties arise from how the brain forms the units of conscious visual perception; namely, representations of three-dimensional boundaries and surfaces. Boundaries and surfaces are computed in parallel cortical processing streams that obey computationally complementary properties. These streams interact at multiple levels to overcome their complementary weaknesses and to transform their complementary properties into consistent percepts. The article describes how properties of complementary consistency have guided the creation of many great works of art.

Ubuntu, Jesus, and Earth: Integrating African Religion and Christianity in Ecological Ethics

Africa faces problems of ecological devastation caused by economic exploitation, rapid population growth, and poverty. Capitalism, residual colonialism, and corruption undermine Africa's efforts to forge a better future. The dissertation describes how in Africa the mounting ecological crisis has religious, political, and economic roots that enable and promote social and environmental harm. It presents the thesis that religious traditions, including their ethical expressions, can effectively address the crisis, ameliorate its impacts, and advocate for social and environmental betterment, now and in the future. First, it examines African traditional religion and Christian teaching, which together provide the foundation for African Christianity. Critical examination of both religious worldviews uncovers their complementary emphases on human responsibility toward planet Earth and future generations. Second, an analysis of the Gwembe Tonga of Chief Simamba explores the interconnectedness of all elements of the universe in African cosmologies. In Africa, an interdependent, participatory relationship exists between the world of animals, the world of humans, and the Creator. In discussing the annual lwiindi (rain calling) ceremony of Simamba, the study explores ecological overtones of African religions. Such rituals illustrate the involvement of ancestors and high gods in maintaining ecological integrity. Third, the foundation of the African morality of abundant life is explored. Across Sub-Saharan Africa, ancestors' teachings are the foundation of morality; ancestors are guardians of the land. A complementary teaching that Christ is the ecological ancestor of all life can direct ethical responses to the ecological crisis. Fourth, the eco-social implications of ubuntu (what it means to be fully human) are examined. Some aspects of ubuntu are criticized in light of economic inequalities and corruption in Africa. However, ubuntu can be transformed to advocate for eco-social liberation. Fifth, the study recognizes that in some cases conflicts exist between ecological values and religious teachings. This conflict is examined in terms of the contrast between awareness of socioeconomic problems caused by population growth, on the one hand, and advocacy of a traditional African morality of abundant children, on the other hand. A change in the latter religious view is needed since overpopulation threatens sustainable living and the future of Earth. The dissertation concludes that the identification of Jesus with African ancestors and theological recognition of Jesus as the ecological ancestor, woven together with ubuntu, an ethic of interconnectedness, should characterize African consciousness and promote resolution of the socio-ecological crisis.

BoostMap: A Method for Efficient Approximate Similarity Rankings

This paper introduces BoostMap, a method that can significantly reduce retrieval time in image and video database systems that employ computationally expensive distance measures, metric or non-metric. Database and query objects are embedded into a Euclidean space, in which similarities can be rapidly measured using a weighted Manhattan distance. Embedding construction is formulated as a machine learning task, where AdaBoost is used to combine many simple, 1D embeddings into a multidimensional embedding that preserves a significant amount of the proximity structure in the original space. Performance is evaluated in a hand pose estimation system, and a dynamic gesture recognition system, where the proposed method is used to retrieve approximate nearest neighbors under expensive image and video similarity measures. In both systems, BoostMap significantly increases efficiency, with minimal losses in accuracy. Moreover, the experiments indicate that BoostMap compares favorably with existing embedding methods that have been employed in computer vision and database applications, i.e., FastMap and Bourgain embeddings.

Genetically Generated Neural Networks I: Representational Effects

This paper studies several applications of genetic algorithms (GAs) within the neural networks field. After generating a robust GA engine, the system was used to generate neural network circuit architectures. This was accomplished by using the GA to determine the weights in a fully interconnected network. The importance of the internal genetic representation was shown by testing different approaches. The effects in speed of optimization of varying the constraints imposed upon the desired network were also studied. It was observed that relatively loose constraints provided results comparable to a fully constrained system. The type of neural network circuits generated were recurrent competitive fields as described by Grossberg (1982).

Genetically Generated Neural Networks II: Searching for an Optimal Representation

Genetic Algorithms (GAs) make use of an internal representation of a given system in order to perform optimization functions. The actual structural layout of this representation, called a genome, has a crucial impact on the outcome of the optimization process. The purpose of this paper is to study the effects of different internal representations in a GA, which generates neural networks. A second GA was used to optimize the genome structure. This structure produces an optimized system within a shorter time interval.