Abhishek Singh
About Abhishek Singh
Projects: Sarcasm Detection Analyzed the headlines of the articles from news sources and detect whether they are sarcastic or not. Achieving .94 ACCURACY in prediction, utilizing Glove and RNN Word embedding LSTM Classification Face Detection Recognized, identified, and classified faces within images using CNN and image recognition algorithms. Improved DICE COEFFICIENT to .61, utilizing Computer Vision, CNN, Transfer Learning, Object detection, Ensemble Techniques and SVM. Face Recognition Built a face recognition system, which locates the position of a face in an image and a face identification model to recognize whose face it is by matching it to the existing database of faces. Improved EMBEDDING ACCURACY .967, utilizing Computer Vision, Keras, CNN, Siamese Networks, Triplet loss and PCA. Image classification neural network to classify Street House View Numbers Image classification of SVHN, real-world image dataset to identify street house number. Utilized Neural Networks, Deep Learning, Keras, Image Recognition. Pushed testing ACCURACY to .9114 using CNN, feature engineering and hyperparameter tuning. Classifying silhouettes of vehicles Classified vehicles into different types based on silhouettes which may be viewed from many angles. Used PCA to reduce dimensionality and SVM for classification. Improved ACCURACY to .863, utilized Support Vector Machines, Principal Component Analysis, Unsupervised Classification Product Recommendation Systems This project involved building recommendation systems for Amazon products. A popularity-based model and a collaborative Filtering model were used and evaluated to recommend top-10 products for a user. Utilized Collaborative Filtering, Recommender Systems in Python. Best approach with RMSE of 1.0552, followed by item-item and SVD. Skills: Azure Machine learning: Azure ML Ops, Azure Cognitive Services, Azure Artificial Intelligence. Python libraries: (sklearn, opencv, tensorflow, keras, nltk, cntk, pandas, numpy, matplotlib, pytorch, seaborn, tkinter, selenium). Machine Learning Concepts: Support Vector Machines, Principal Component Analysis, Classification, Regression, Decision trees, Feature Engineering, Collaborative Filtering, Recommender Systems, Neural Networks, Deep Learning, Keras, Image Recognition, EDA, Data visualization and statistical Inference. SQL Server: Core, Architecture, Performance, High availability, Security, Designing Stored Procedures. Azure components: Azure Data lakes, Azure Cluster instance, Azure Kubernetes Service, Power BI, Azure Databricks.