Tag: Artificial intelligence
-
Pure2DopeNet: Multimodal Neural Network-Based Predictive Modeling of Nanoparticle Properties from Pure Compounds
Can Polat, Mustafa Kurban, and Hasan Kurban – IOP’s Machine Learning: Science and Technology
-
Extended abstract of our IEEE DSAA24 paper is now available
The extended abstract of our paper, “p-ClustVal: A Novel p-adic Approach for Enhanced Clustering of High-Dimensional scRNASeq Data” is available at IEEE Xplore (https://ieeexplore.ieee.org/document/10722799)
-
Enhancing Cluster Discernment in High Dimensional Single Cell RNA Sequencing Data
Excited to share that our recent work on using alternate data representation for enhancing cluster discernment in high dimensional single cell RNA Sequencing data has been accepted at the 11th IEEE International Conference on Data Science & Analytics (DSAA 2024).
-
QuantumShellNet: Ground-State Eigenvalue Prediction of Materials Using Electronic Shell Structures and Fermionic Properties via Convolutions
Can Polat, Hasan Kurban, and Mustafa Kurban – Elsevier’s Computational Materials Science.
-
Temporal Graph Neural Networks
Introduction Due to the increasing connectivity in the world, graph data has manifested itself in many contexts, particularly in recent years. Analyzing interactions within graphs makes for an interesting exploration across many applications. While many studies concentrate on static graphs, the changing nature of data requires examining how interactions within a graph change over time.
-
PlayoffsNet: Enhancing NBA Playoffs Prediction Through Engineered Features and Explainable Deep Learning
Ganesh Arkanath, Hasan Kurban, Mehmet Dalkilic – ACM KDD 2025 (under-review)
-
An Extended de Bruijn Graph for Feature Engineering Over Biological Sequential Data
Mert Onur Cakiroglu, Hasan Kurban, Parichit Sharma, M Oguzhan Kulekci, Elham Khorasani Buxton, Maryam Raeeszadeh-Sarmazdeh, Mehmet M Dalkilic – Machine Learning: Science and Technology
-
Materials as Graphs
Introduction Graph Neural Networks (GNNs) have emerged as a critical tool for modeling complex relationships and interactions in data, particularly in fields such as social and physical sciences. In this blog, we delve into the applications of GNNs in materials science (MS), an interdisciplinary field that combines elements of physics, chemistry, and engineering to understand
-
Advolance: Next-Generation Educational Software
In recent years, generative AI technology has become an integral part of our lives, transforming various sectors from content creation to customer service. Now, we are excited to bring this revolutionary technology to programming education with our innovative web software. Our collaborative text editor for learning Python harnesses the power of generative AI to provide
-
Special Session: Advancing Materials Science with Data Science – IEEE DSAA 2024
We are glad to announce that we are organizing the special session-“Advancing Materials Science Through Data Science:Innovations, Applications and Challenges” at 11th IEEE, International Conference on Data Science & Analytics, 2024. Many thanks to all those who submitted their papers. We will see you all there 🙂 More Info: https://www.dsaa2024-specialsession-data-driven-material-science.com/homepage
-
Accepted Paper: Enhancing K-Means with Data-Centric AI
Our paper – “What Data-Centric AI can Do for Kmeans: a Faster, Robust Kmeans-d” has been accepted at the Proceedings of the 41st International Conference on Machine Learning (ICML), Data-Centric Machine Learning Workshop (DMLR), to be held in Vienna, Austria.
-
A Reinforcement Learning Approach to Effective Forecasting of Pediatric Hypoglycemia in Diabetes I Patients: an extended de Bruijn Graph
Mert Onur Cakiroglu, Hasan Kurban, Khalid Qaraqe, Lilia Aljihmani, Goran Petrovski, Mehmet Dalkilic – Scientific Reports (under-review)
-
Text-To-Energy–Accelerating Quantum Chemistry Calculations through Enhanced Text-to-Vector Encoding and Orbital-Aware Multilayer Perceptron
Can Polat, Hasan Kurban, Mustafa Kurban – Scientific Reports (under-review)
Kurban Intelligence Lab 