Learn More
This paper demonstrates that feature acquisition systems composed of spiking neurons trained by spike-timing-dependent plasticity (STDP) can effectively be scaled using General-Purpose computing on Graphics Processing Units (GPGPU). Previous studies have demonstrated the efficacy of such systems for classes with low intra-class variability. Parallelization(More)
Illegal drag racing or street racing is a prominent safety concern in many major cities. This is especially the case in areas which have sections of road which are straight, level, and have low traffic at various times of day or night. This paper proposes a control mechanism for a system which is capable of detecting illegal street races and reporting them(More)
This paper examines the effects of parallelizing an unsu-pervised feature acquisition algorithm using General-Purpose computing on Graphics Processing Units (GPGPU). Previous work in feature learning has established the effectiveness of hierarchical learning methods that refine large quantities of elementary features into small numbers of intermediate-level(More)
  • 1