Our research focuses on development of deep learning, machine learning, data mining, and evolutionary algorithms for scientific discovery and engineering innovation in materials science, bioinformatics, health informatics, function genomics, medical and health sciences, engineering designs, intelligent manufacturing and etc. We are specialized in developing state-of-art pattern recognition, classification, regression, predictive modeling, inverse design using state-of-the-art models such as deep neural network models, generative adversarial networks, graph neural networks, genetic programming, symbolic regression.
Our lab has the first-class computing facilities for deep learning, AI, and big data research. We welcome collaborators with data analysis and pattern discovery problems in biology, materials, education, medicine and any discipline with big data. Just contact us at: jianjunh at cse.sc.edu
|Quantum GPU Server|
4 2080Ti GPU
2Tb SSD+10Tb HD
| Powerful Deep learning server with 4 Nvidia Titan 2080Ti GPUs. Intel 12 core 24 threads CPU.
|Origin GPU Server|
3 Titan 2080Ti GPUs
| Powerful deep learning GPU server with 3 Titan 2080Ti, AMD Ryzen 32 core 64 threads CPU and 128GB memory. |
|Angel GPU Server|
1 Titan RTX GPU
24GB GPU memory + 128GB CPU memory
| Powerful deep learning GPU server with 1 Titan RTX, intel 8 core CPU and 64GB memory. |
|Evolution GPU Server|
1 Titan V GPU
24GB GPU memory + 64GB CPU memory
| Powerful deep learning GPU server with 1 Titan V,5120 GPU cores, 12GB GPU memory, intel 8 core CPU and 64GB memory. |
|University Supercomputer Hyperion|
86 Powerful deep learning GPU servers each with Titan V100 GPU memory 48GB, intel 16 core CPU and 128GB memory..
| The newest cluster, Hyperion, has 224 compute nodes, 8 GPU nodes and 8 large memory nodes providing 6,760 CPU cores for faculty and students in the Columbia campus. Located in the campus data center, compute, GPU, Big Data nodes, and 330 TB of Lustre and NFS data storage are interconnected over a high-speed 100 Gigabit InfiniBand network. Enterprise-level cooling, battery backup, generator backup, and physical security are provided through the data center. The USC datacenter provides enterprise-level cooling, battery backup, generator backup, and physical security. Hyperion is USC’s flagship cluster intended for large, parallel jobs. Compute and GPU nodes have 128 GB of RAM and Big Data nodes have 1.5 TB RAM.|