This project is no longer accepting applications. Subscribe to our newsletter to be notified of new projects!
Develop an AI-driven application that uses machine learning models and vector databases to retrieve relevant images based on visual queries
Efficient image retrieval systems are crucial across multiple sectors, including media, e-commerce, and education. This Build Project offers a gateway into the essential AI and machine learning work that underpins advanced technology careers, particularly in firms that are leading the innovation in digital content management and user interface technologies.
During this Build Project, you will step into the role of a Data Scientist, tasked with developing an AI-powered image retrieval system using state-of-the-art technologies and methodologies. Guided by a seasoned industry professional, you will gain skills to conduct research and explore machine learning frameworks and develop software using vital production tools such as Python, PyTorch, FAISS, and Docker.
Install and configure essential software and tools necessary for the project, including Python, Miniconda, Docker, FAISS, and Jupyter notebooks.
Understand and prepare the image dataset, learn to extract meaningful features, and use visualization techniques.
Use feature vectors to identify and remove anomalies and implement data transformations to enhance the usability of the data.
Learn the architecture and training process of neural networks, implement loss functions, and analyze training and validation loss curves.
Identify signs of underfitting and overfitting, implement data augmentation, and apply regularization methods.
Calculate performance metrics and integrate the trained model with FAISS.
Package and deploy the model using Docker and integrate it into a Streamlit web application .
Deliver a comprehensive presentation and demonstrate the fully functional image retrieval application.
Get access to all of our Build projects, including this one, by creating your Build account!
Get started by submitting your application.
We'll notify you of new projects via email. In the meantime, you can explore our resources and learn more about our Fellows.
Kamalesh Kalirathinam is a Data Science Build Fellow at Open Avenues, where he works with students leading projects in Data Science.
Kamalesh is a Data Scientist at RadiusAI, where he focuses on developing and optimizing complex neural networks that can identify thousands of products in real-time, assisting cashiers with an AI solution in the retail space.
Kamalesh has over 3 years of experience in the Data Science field. His expertise spans computer vision, natural language and deep learning, with a particular focus on real-world applications of AI technology.
He holds a Master’s Degree in Artificial Intelligence and Robotics.
A fun fact about Kamalesh is that he loves playing guitar and builds robots in his free time.