Hire Karan K. - Data Scientist

Currently working with client Lenovo to predict computer crashes by analyzing data and training machine learning models. Implementing feature engineering, feature selection, explanatory data analysis and cleaning data before evaluating machine learning model’s performance.

Successfully completed working on classifying vehicles, pedestrians, and bicycles in front of the car. Implementing Hog Classifiers on OpenCV to collect features of different objects and training Support Vector Machines (SVM) on AWS EC2 to classify the objects on the NVIDIA Jetson TX2. => Implemented transfer learning on ImageNet using feature extraction to successfully classify traffic signs with an accuracy of 97% on Tensorflow using Python 3.6 => Built a pipeline using distortion correction, image rectification, color transforms and gradient thresholding to identify lane lines and their curvature for the self – driving car. => Cloned the behavior of the car using a Deep Neural Net architecture with a combination of 5 Convolutional layers and 4 fully connected layers to predict the steering angle of the car at any given point of time with a validation loss of 0.0183 in Python.