Convolutional neural networks (CNNs) are widely used in pattern-and image-recognition problems as they have a number of advantages compared to other techniques. This white paper covers the basics of CNNs including a description of the various layers used. Using traffic sign recognition as an example, we discuss the challenges of the general problem and introduce algorithms and implementation software developed by Cadence that can trade off computational burden and energy for a modest degradation in sign recognition rates. We outline the challenges of using CNNs in embedded systems and introduce the key characteristics of the Cadence� Tensilica� Vision P5 digital signal processor (DSP) for Imaging and Computer Vision and software that make it so suitable for CNN applications across many imaging and related recognition tasks.