Gauri Sharma

To seek and maintain full-time position that offers professional challenges utilizing interpersonal skills, excellent time management and problem-solving skills.

• Academic Scholarship - Scored among the top 5 positions in the entire batch. (2010, 2011)
• Cleared the National Mathematics Talent Contest (NMTC), a highly reputed mathematics contest, organized by AMTI. (2010)
  Cleared level 1 by being in the top 10 percent scorers in the entire registration zone of Haryana. Qualified for level 2.
• International Rank 342, 11th National Cyber Olympiad, 2011.
• Scholar Medal (Principal's Gold Medal)- Received a Gold Medal for 7 consecutive years of Academic Excellence.
  (2006-2012).
• Gold Medalist - 2010, 2011. Issuer: Delhi Public School, Faridabad.

• Mask R-CNN with OpenCV for Object Detection : I used R-Mask CNN model with inception 2. The R-CNN is does detection in multiple stage with multiple CNN passes. At first it generated proposal regions by studying pixel gradients and edges. Classification is run on each proposal. The final results and bounding boxes are then obtained post-processing of the individual results.
  
• Image Classification with Pre-trained Keras models : Created using resnet50 which was originally trained to classify the ImageNet data. I used this model to predict the class of an input image. Worked on understanding the different steps of preprocessing this input image as required by the network, before predicting the class of the image.
  
• Stock Closing Price Prediction using Deep Learning, TensorFlow2 & Keras : In this project, I worked on how to predict stock market closing prices for a firm using GRU, a state-of-art deep learning algorithm for sequential data.
  Focused on data cleaning and data modeling to build a predictive model for stock market closing prices.
  
• Training from Scratch vs Transfer Learning : The objective of the project is - to use Fashion-MNIST data set to identify (predict) different fashion products(articles) from the given images using Machine Learning.
  
• Crime Rate Detection Analysis : K - means algorithm plays an important role in analyzing and predicting crimes . K - means algorithm clusters co-offenders, collaboration and dissolution of organized crime groups, identifying various relevant crime patterns, hidden links, link prediction and statistical analysis of crime data.
  Tools: RapidMiner (Data Science software platform that provides an integrated environment for data preparation , machine learning , deep learning, text mining, and predictive analytics ).