Published:
Course Overview:
This course provided a comprehensive introduction to core machine learning models and algorithms, covering key concepts in classification, regression, clustering, and dimensionality reduction. It balanced theoretical understanding with practical application, allowing students to grasp both the mathematical foundations and the real-world usage of machine learning techniques.
Published:
Course Overview:
COMPSCI 682 is a 3-credit course focused on modern and practical methods for deep learning. The course began with an introduction to simple classifiers such as perceptrons and logistic regression and progressively moved into more complex topics, including standard neural networks, convolutional neural networks, and elements of recurrent neural networks and transformers. While the course provided a strong emphasis on practical applications, it maintained a solid foundation in the fundamentals of deep learning.
Published:
Course Overview:
COMPSCI 532: Systems for Data Science is a 3-credit course designed to provide students with a deep understanding of the systems and infrastructures that underpin large-scale data science. The course focuses on the principles and challenges associated with scaling computational processes both vertically (to many processors) and horizontally (to many nodes), enabling efficient and fast analyses of large datasets.
Published:
Course Overview:
Natural Language Processing (NLP) is both an engineering art and a science, focused on teaching computers to understand human language. As a subset of artificial intelligence, NLP has become ubiquitous, powering voice assistants, web-based question answering, discussion analysis in social media, and even human language translation. The complexity of language—rich in nuances and ambiguity—makes it challenging for computers to understand, but through the application of data, mathematics, and linguistic insights, these engineering problems can be tackled.
Published:
Course Overview:
This graduate-level course delves into the sophisticated techniques for analyzing visual data, particularly color images. The course is structured in two key parts:
Published:
Develop a system that detects and classifies objects in satellite or aerial imagery, such as buildings, roads, and natural landmarks, and uses geolocation data to map them accurately. This could be used for urban planning, disaster response, or environmental monitoring
Published:
Exploring the integration of emotion recognition with neural style transfer to create visually and emotionally enriched images.
Published:
Our project has explored ways to improve camouflaged object segmentation performance in a limited data setting.
Published:
A novel system to evaluate prompt specificity and its impact on Large Language Model performance.
Published:
This page is still being worked upon and will be available soon.
Published:
This page is still being updated and will be available soon.