Hardware implementations of spiking neurons can be extremely useful for a large variety of applications, ranging from high-speed modeling of large-scale neural systems to real-time behaving systems, to bidirectional brain–machine interfaces. The specific circuit solutions used to implement silicon neurons depend on the application requirements. In this paper we describe the most common building blocks and techniques used to implement these circuits, and present an overview of a wide range of neuromorphic silicon neurons, which implement different computational models, ranging from biophysically realistic and conductance-based Hodgkin–Huxley models to bi-dimensional generalized adaptive integrate and fire models. We compare the different design methodologies used for each silicon neuron design described, and demonstrate their features with experimental results, measured from a wide range of fabricated VLSI chips.

No abstract

No abstract

SUMMARYEarly ocular disease diagnosis is an important field in medical research. From the image processing point of view, many strategies and algorithms have been developed to deal with the extraction of the retinal vessel tree. Although reliable and accurate results have been obtained, the main disadvantage in most of these proposals is the high computation effort required. In this paper, a methodology to extract the retinal vessel tree has been developed and tested in a fine-grain pixel-parallel processor array. An analysis of the execution time has been made to demonstrate its capabilities regarding the computation speed. Moreover, an analysis of the accuracy using a publicly available database has been made to validate the algorithm performance.

Camera sensors rely on global or rolling shutter functions to expose an image. This fixed function approach severely limits the sensors' ability to capture high-dynamic-range (HDR) scenes and resolve high-speed dynamics. Spatially varying pixel exposures have been introduced as a powerful computational photography approach to optically encode irradiance on a sensor and computationally recover additional information of a scene, but existing approaches rely on heuristic coding schemes and bulky spatial light modulators to optically implement these exposure functions. Here, we introduce neural sensors as a methodology to optimize per-pixel shutter functions jointly with a differentiable image processing method, such as a neural network, in an end-to-end fashion. Moreover, we demonstrate how to leverage emerging programmable and re-configurable sensor-processors to implement the optimized exposure functions directly on the sensor. Our system takes specific limitations of the sensor into account to optimize physically feasible optical codes and we demonstrate state-of-the-art performance for HDR and high-speed compressive imaging in simulation and with experimental results. Index Terms-high-dynamic range imaging, video compressive sensing, high-speed imaging, programmable sensors, vision chip, deep neural networks, end-to-end optimization !

No abstract

No abstract

No abstract