Selçuk Talay

Learn More
In this paper we present a scalable hardware architecture to implement large-scale convolutional neural networks and state-of-the-art multi-layered artificial vision systems. This system is fully digital and is a modular vision engine with the goal of performing real-time detection, recognition and segmentation of mega-pixel images. We present a performance(More)
We present a scalable hardware architecture to implement large-scale bio-inspired synthetic vision systems. The system is a fully digital implementation of a modular vision engine that can perform real-time detection, recognition and segmentation of mega-pixel images. We present performance comparisons between software versions of the vision system(More)
Overloading of the integrators in loop filter of Sigma-Delta modulators is a performance degrading factor in circuit implementations. In this paper, it is shown that in resonator-based Â∆ modulators scaling factors should be introduced in order to adjust the integrators' input. A systematic method is presented to calculate these scaling factors without(More)
A method for a smart selection and sequencing of unity capacitors in a multibit DAC is proposed. The approach, suitable for the DAC nonlinearity correction in Sigma-Delta modulators, obtains results that are better than the Dynamic Element Matching. Key of the technique is an off-line selfmeasurement of mismatches. The results significantly improve when the(More)
In this work, recent low-power decimation filter architectures of Sigma-Delta analog-todigital converters are presented and an improved version is proposed. Most of the available studies are focused on the analog part of Sigma-Delta architectures. However, the digital part can also be designed as lowpower. This work presents a low-power and area design of(More)