Mahmut Kandemir

AI-related Expertise Topics

• Architecture and system support for AI and ML
• Automated ML application-to-hardware mapping strategies
• Compiler-directed code optimizations for ML applications
• Optimizations for Graph Neural Networks
• Drug Discovery

Externally Funded AI Projects

• NSF SHF: Small: Software and Hardware Optimizations for Learning over Graphs; Award Number:2008398; PI: Mehrdad Mahdavi; Co-PI: Mahmut Taylan Kandemir; Date:10/01/2020; Award Amount:$500,000.00

AI-related Courses

• CSE598: Hand-On Deep Learning
• CSE598: Machine Learning for Health Analytics

Webpage

www.cse.psu.edu/hpcl/kandemir

Related Publications

• Weilin Cong, Rana Forsati, Mahmut T. Kandemir, Mehrdad Mahdavi: Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks. KDD 2020: 1393-1403
• Morteza Ramezani, Weilin Cong, Mehrdad Mahdavi, Anand Sivasubramaniam, Mahmut T. Kandemir: GCN meets GPU: Decoupling "When to Sample" from "How to Sample". NeurIPS 2020
• Huaipan Jiang, Mengran Fan, Jian Wang, Anup Sarma, Shruti Mohanty, Nikolay V. Dokholyan, Mehrdad Mahdavi, Mahmut T. Kandemir: Guiding Conventional Protein-Ligand Docking Software with Convolutional Neural Networks. J. Chem. Inf. Model. 60(10): 4594-4602 (2020)
• Mengran Fan, Jian Wang, Huaipan Jiang, Yilin Feng, Mehrdad Mahdavi, Kamesh Madduri, Mahmut T. Kandemir, and Nikolay V. Dokholyan: GPU-Accelerated Flexible Molecular Docking:  The Journal of Physical Chemistry B 2021 125 (4), 1049-1060, DOI: 10.1021/acs.jpcb.0c09051
• Diana Guttman, Mahmut Taylan Kandemir, Meena Arunachalam, Rahul Khanna:Machine learning techniques for improved data prefetching. In Proc. ICEAC 2015: 1-4ashwant Raj Gunasekaran, Prashanth Thinakaran, Cyan Subhra Mishra, Mahmut Taylan Kandemir, Chita R. Das: Towards Designing a Self-Managed Machine Learning Inference Serving System in Public Cloud. under revision, 2021