An End-to-End Speech Recognition System using existing research. given audio data that convert Analog-to-Digital using (ADC) converter, then extract features form audio using some Signinal-Processing algorithms like Sort-Time-Fourier-Transform(STFT), Then using some Deep-Learning based techniques (like CNN's, LSTM's and GRU's) convert audio features into text representation

Face Recognition using FaceNet Inception Resnet (V1) model in pytorch and using state of the art Face Detection model called Retina Faces

Uncover the factors to help measure how young children learn. In this competition use gameplay data to forecast how many attempts a child will take to pass a given assessment. I got my first Kaggle Medal (Silver) top 3%

Extract support phrases for sentiment labels. We are using transformer models like BERT, RoBERTa, Albert, XLM-RoBERTa, XLNet using TPU’s, and GPU’s for training.

Amazon Fine Food Reviews is a classic Sentiment Analysis problem used to classify the polarity of the review given by Amazon user. Given the textual reviews and related features of the product, I have designed various techniques to classify the polarity of the review.

In this project, Identfy which questions asked on Quora are duplicates of questions that have already been asked. This colud be useful to instantly provide answers to questions that have already been answered. We are tasked with predicting whether a pair of questions are duplicates or not , using Machine Learning Models like Linear SVM , Logistic Regression, XgBoost .

In this project, Given a directed social graph, have to predict missing links to recommend users (Link Prediction in graph ) . Taken data from facebook’s recuting challenge on kaggle and Mapping the problem into supervised learning problem . Using Liner SVM , Predicting missing links to recommend users using Machine Learning Models like Linear SVM , Logistic Regression, XgBoost .

Build a recommendation engine which suggests similar products (apparel) to the given product (apparel) in any e-commerce websites. This work is done as a part of the workshop conducted by Applied AI Course on Amazon Apparel Recommendation Engine. The data has been taken from Amazon.com in a policy compliant manner.