This report deals with translation invariance of convolutional neural networks (CNNs) for automatic target recognition (ATR) from synthetic aperture radar (SAR) imagery. In particular, the translation invariance of CNNs for SAR ATR represents the robustness against misalignment of target chips extracted from SAR images. To understand the translation invariance of the CNNs, we trained CNNs which...

Artificial Neural Networks became a common solution for a wide variety of problems in many fields, such as control and pattern recognition to name but a few. Many solutions found in these and other Artificial Neural Network fields have reached a hardware implementation phase, either commercial or with prototypes. The most frequent solution for the implementation of Artificial Neural Networks co...

The present thesis aims at proposing a new oscillatory neural network and at implementating using a massively parallel architecture, which is suitable to the implementation of digital vision chips for image segmentation. The final version of the proposed network called ONNIS-GI (Oscillatory Neural Network for Image Segmentation with Global Inhibition) was inspired on a network called LEGION (Lo...

Multi-electrode arrays (MEAs) can be used for noninvasive, real-time, and long-term recording of electrophysiological activity and changes in the extracellular chemical microenvironment. Neural network organization, neuronal excitability, synaptic and phenotypic plasticity, and drug responses may be monitored by MEAs, but it is still difficult to measure presynaptic activity, such as neurotrans...

A neural net program for pattern classification is presented, which includes: i) an improved version of Kohonen's Learning Vector Quantization (LVQ with Training Count); ii) Feed-Forward Neural Networks with Back-Propagation training; iii) Gaussian (or Mahalanobis distance) classification; iv) Fisher linear discrimination. Back-Prop trainings with emulations of Intel's ETANN and Siemens' MA16 n...

The goal of this study was improvement of sandy soil using a combination of polystyrene foam container waste and Portland cement. For this purpose, Babolsar sand was used as the base soil. Strips of disposable polystyrene foam container waste in “chips” of 50 ´ 5 mm and 50 ´ 10 mm were added to the soil at 0.0%, 0.1%, 0.2% and 0.3% by weight along with 3% Portland cement at a relative density o...

Neuromorphic embodied cell assembly agents that learn are one application being developed for the Human Brain Project (HBP). The HBP is building tools, available for all researchers, for building brain simulations. Existing simulated neural Cell Assembly agents are being translated to the platforms provided by the HBP; these agents run on neuromorphic chips in addition to von Neumann based comp...

This paper presents a systematic approach to design CMOS chips with concurrent picture acquisition and processing capability. Pixel smartness is achieved by exploiting the Cellular Neural Network paradigm [1], incorporating at each Spixel an analog computing cell which interacts with those of nearby Spixels. We propose a current-mode technique for CNNSpixel chips and give measurements from two ...

Cascadable, CMOS synapse chips containing a cross-bar array of 32x32 (1024) programmable synapses have been fabricated as "building blocks" for fully parallel implementation of neural networks. The synapses are based on a hybrid digital-analog design which utilizes on-Chip 7-bit data latches to store quantized weights and two-quadrant multiplying DAC's to compute weighted outputs. The synapses ...