In animal brains, computation, and other functions emerge from the interaction of neural areas.

Brain networks express modular, small-world, heavy-tailed characteristics. In small-world networks, most edges form small, densely connected clusters, while others maintain connections between these clusters. By restricting the neuromorphic processor to implement small-world SNNs, we can dramatically reduce the memory required to specify the routing and connectivity schemes while still supporting a wide range of computations for solving pattern recognition and signal processing tasks.

Keywords: Neuromorphic Processors, Compilers, Hierarchical Routing, Small-world Networks, Multi-core, Cortical Networks, Neuromorphic Ecosystem

Brain-inspired event-based neuromorphic processing systems have emerged as a promising technology for bio-medical circuits and systems. However, both neuromorphic and biological implementations of neural networks have critical energy and memory constraints.

To minimize the use of memory resources in multi-core neuromorphic processors, we propose a network design approach inspired by biological neural networks. We use this approach to design a new routing scheme optimized for small-world networks and, at the same time, to present a hardware-aware placement algorithm that optimizes the allocation of resources for small-world network models.

We validate the algorithm with a canonical small-world network and present preliminary results for other networks derived from it.

In this work, we present a neuromorphic architecture for head pose estimation and scene representation for the humanoid iCub robot. The spiking neuronal network is fully realized in Intel's neuromorphic research chip, Loihi, and precisely integrates the issued motor commands to estimate the iCub's head pose in a neuronal path-integration process. The neuromorphic vision system of the iCub is used to correct for drift in the pose estimation. Positions of objects in front of the robot are memorized using on-chip synaptic plasticity. We present real-time robotic experiments using 2 degrees of freedom (DoF) of the robot's head and show precise path integration, visual reset, and object position learning on-chip. We discuss the requirements for integrating the robotic system and neuromorphic hardware with current technologies.

Lithology classification is an essential task in oil reservoir characterization, and one of its primary purposes is to support the well planning and drilling activities.
Therefore, faster and more effective classification algorithms will increase the speed and reliability of decisions made by geologists and geophysicists.

This work analyses ensemble methods applied to automatic lithology classification. For this, we compare single classifiers (Support Vector Machines and Multilayer Perceptron) and these classifiers with Ensemble methods (Bagging and Boost). We conclude with a comparative evaluation of techniques and present the trade-off in using Ensemble methods to replace single classifiers.

​

Keywords: Lithology, Ensemble Methods, Support Vector Machines, Multilayer Perceptron, Neural Networks.

Urban virtual models have been used to preserve architectural heritage or predict and simulate situations of real environments. Thus, we used virtual reality to make a virtual tour through the Historic Center of Sao Luis, considered a world cultural heritage site, using an optimization algorithm based on a Spatial Database to allow the visualization of urban models. The three-dimensional modeling of the city used the X3D, an open standard for content distribution in three dimensions. The X3D combines features of both geometry and descriptions of behavior, being described by the Web3D Consortium.

​

Keywords: Virtual Reality, Urban Virtual Model, Geoespatial Databases, X3D.

This chapter aims to investigate the adequacy of the reinforcement learning techniques to classify lesions based on medical images. We show the application of this technique to classify lung nodules (to be malignant or benign). We use 3D geometric measures extracted from lung lesions Computerized Tomography (CT) images.