Chief Research Officer2016 - 2018F(x) Data Labs
Technologies: Python, R, TensorFlow, TFLearn, Caffe, Torch, Keras, DNN, CNN, MySQL, C/C++, PHP/Laravel, OpenStack, QEMU, Angular4, Vagrant, NLP, MATLAB
- Contributed in refining h+Tree algorithm which is 300% faster technology than currently used b+Tree.
- Developed a full-stack public cloud with IaaS, DBaaS, NaaS, OaaS, VPN. Worked extensively on Virtualization and virtual networking.
- Created a resume parser to parse all the details from the resume into the appropriate format.
- Analyzed historical data using machine learning. Implemented the machine learning based model which can calculate the user’s conversion probability from the historical data.
- Created a text classification algorithm using word vector embeddings to classify event types from the event description.
- Created an algorithm for an eCommerce site to identify when will particular item gets out-of-stock using RNN LSTM.
- Implemented convolutional neural network on the MRI of the brain to classify the brain tumor in five different classes.
- Created an algorithm for lottery prediction using RNN LSTM and AdaBoost algorithm along with Python.
- Created a chatbot which can answer with reasoning using artificial intelligence. It uses Wikipedia dataset and trained using CNN-RNN.
- Built an algorithm that finds the content of the images and videos in terms of Objects and Scenes. For this, I have used Convolutional Neural Networks, TensorFlow, and Keras.
- Developed an algorithm for operation room scheduling for hospitals using artificial neural networks, Python, Laravel, Angular4, CSS3, and Vagrant.
- Deployed the generative adversarial networks and created an algorithm to generate an image from text. It takes text description as an input and creates an image according to the text input.
Machine Learning Developer2013 - 2016Self-employed
Technologies: Python, Torch, Vagrant, OpenCV, CNN, DNN, HMM-GMM, SVM, Sirius
- Developed an algorithm to generate a 3D model of faces from a single 2D mobile selfie using Python, Convolutional Neural Networks, PyTorch, and CUDA.
- Created an algorithm for image and video compression using similarity between images with the help of OpenCV.
- Developed an algorithm for classification of different sounds of drones using MFCC and LPCC features and then SVM and HMM-GMM classifiers.
- Developed an algorithm for speech assistant, using Sirius: An Open Intelligent Personal Assistant.
- Created a default loan predictor algorithm with 99.4% accuracy using Python and deep neural networks.
- Created an optical character recognition for Gujarati language using Python and OpenCV,.
- Extracted the legos from the videos and the classify it into 52 different classes using the convolutional neural network using Python.
- Worked on the CNN based binary text classification for the movie reviews to identify the positive and negative reviews with neural networks and Python.
- Developed an algorithm for moving object detection, which can find a moving object in a vibrant environment using deep neural networks, OpenCV, and Python.