I am doing my Bachelor of technology in Computer Science Engineering. I have a good knowledge about Machine Learning, Data structures and object-oriented programming. I am always curious to learn new technologies and I like to complete my work on time. In my free time I listen to podcasts, read books and enjoy running in morning.
DevOps
DevOps represents a change in IT culture, focusing on rapid IT service delivery through the adoption of agile, lean practices in the context of a system-oriented approach.
Machine Learning
Machine learning is an application of AI that enables systems to learn and improve from experience without being explicitly programmed.
Unreal Engine
Unreal Engine is a complete suite of creation tools for game development, architectural and automotive visualization, linear film and television content creation, broadcast and other real-time applications.
Phishing Detection
A model for detecting whether a given URL is Phishing or Legitimate. This model is made fully from scratch that is working on data collection to making a pipeline for smoothing the process of storing and retrieving the data. Furthermore creating a backend which extract features from the data retrieved from users. Used an Ensemble model (Random Forest) to test our model and the accuracy was above 98%.
Digit Recogniser
An end to end project for detecting numbers. This project is combination of all the model that can be performed to detect numbers. I have used various pretrained models and made ensemble of it. This model preforms well in even the harshest of condition. In testing I have performed its testing on various places like railway equipment numbering, shipment container numbering and many more in different condition and it has performed quite nicely in all of them.
Dogs Vs Cats Classifier
A model which classifies between dogs and cats. CNN model using 'relu' and 'sigmoid'. -Classification and loss as 'binary-crossentropy'. After tuning a hard-coded model the accuracy of the model in test reached till 85%
Food Classifier
A model which classifies different types of food and names them accordingly. The final predictions attained a test set accuracy of 72%. This accuracy was reached by using a weighted ensemble of five pre trained convolutional networks.
