👋 Hello there! I'm Sid, a passionate Computer Science graduate student at Arizona State University (ASU) with a keen interest in the exciting realm of deep learning. As an avid learner and enthusiast, I am thrilled to be an active member of the GitHub community, where innovation and collaboration thrive.

📚 I am wrapping up my Master of Science (MS) degree in Computer Science (Hons.) at ASU, specializing in deep learning and its diverse applications. My academic journey has allowed me to delve into the fascinating world of generative models, exploring how these cutting-edge techniques can revolutionize various industries.

💡 Currently, I am further expanding my skill set by diving into React, eagerly exploring front-end technologies to create dynamic and user-friendly web applications.

⏱️ When I'm not diving into code, you can find me hiking and enjoying the serenity of nature. Additionally, I'm an avid chess player, and I love challenging myself with strategic moves and thrilling chess matches, often playing at the summit during my hiking adventures.

• Calorie counter | Transfer Learning, InceptionV3, ImageNet, Python
  GitHub
  Developed a deep learning model using transfer learning with InceptionV3 architecture and pre-trained weights from the ImageNet dataset. Fine-tuned the model to classify 101 types of foods and accurately estimate their calorie content per gram. Employed data augmentation and advanced regularization techniques for improved generalization. Achieved exceptional results with 95% classification accuracy and precise calorie per gram intake estimation. Implemented an interactive web interface for a user-friendly experience.

• Robo Collision Detector | PyTorch, Pygame, Feed-forward Neural Network
  GitHub
  Trained a PyTorch-based neural network for a robot collision detector. Captured data from random agent movement to prepare the environment. Designed a feed-forward neural network with two hidden layers of 40x40 neurons, utilizing ReLU activation for the hidden layers and sigmoid for the output. Optimized the network using the Adam optimizer with a learning rate of 0.001 and a small batch size of 16 activities. Achieved accurate collision detection by analyzing TP, TN, FP, and FN using the confusion matrix.

• BetterFoods website | Flask, Python, API Integration
  GitHub
  Developed a user-friendly Flask website that utilizes APIs like YELP and Google Maps for seamless restaurant discovery based on ratings and proximity. Integrated the APIs to fetch real-time data, enabling accurate recommendations. Employed SQL databases for efficient data storage and retrieval. Implemented intricate backend logic and contributed to the GitHub repository for collaborative development.

• Beautiful Soup+ Selenium | Python, Web Scraping, Data Parsing
  GitHub
  Developed a robust web scraping and data parsing solution using Beautiful Soup and Selenium libraries in Python. Leveraged these powerful tools to extract and parse data from prominent YouTube coding channels, enabling the ranking of the most popular/viewed channels and identification of the best resources for self-study programming. Implemented advanced techniques to handle dynamic web pages and navigate through complex HTML structures, ensuring accurate and comprehensive data retrieval.