Our solution is an intelligent cervical cancer diagnostic system to aid and assist the procedure of manual detection in a low cost, fast and power-efficient manner and allows for a preliminary diagnosis. our system employs neuromorphic hardware that is inspired by the parallelism of the brain to mimic brain-like functionality for such decision making capabilities. it is a non-invasive, portable, convenient, radiation-free and safe detection method that processes pap smear images, and classifies them as normal or abnormal by testing them on the diagnostic system. we train our neuromorphic hardware solution on existing datasets of classified slide images. for testing, we use a machine-learning algorithm implemented on hardware, that calculates a confidence value of each image belonging either to the normal category or the abnormal category. on the basis of this value of confidence, the sample is either classified as normal or cancerous (as a preliminary diagnosis). we are able to get average speedups of nearly 40 x over existing state-of-the-art implementations in literature with comparable accuracy and drastic power reductions by ~ 500 x per test sample.the portable nature of our solution enables it to be coupled with small portable microscopes that can result in an intelligent mobile diagnostic platform. this work has been accepted for publication and presented at the prestigious ieee biocas conference 2017, turin, italy this year as a part of the smart devices and neuromorphic circuits track.