Explore projects

MINT is a Python package that streamlines integration of multilayer networks for multimodal community detection (subtyping). MINT is comprised of several modules crafted to: standardize input data, execute Spectral Neighbor-joining Fusion (SNF) and Generalized Louvain (GenLouvain) algorithms, visualize intermediate results, perform cross-validation techniques, and optimize the identified communities by selecting an optimal combination of modalities that maximizes the silhouette score.

Contact: Dr. Saman Sarraf (ssarraf@stanford.edu), Dr. Hadi Hosseini (study_brain@stanford.edu)

Xuan's original project found here (https://github.com/xuanyoya/Interstellar-CNN-scheduler), repo adapted for class.

Miscellaneous files that we want to make publicly available.

Materials for Stanford's EE185 course, Interactive Light Sculpture Project.

The Otica project public release repository.

Fine-Grained Memory Access Profiling for GCRAM-Based AI Accelerators. Profiler to provide insight into relevant metrics such as data lifetimes and read/write frequencies to guide DSE of gain cell-based on-chip memories in domain specific hardware.

Backup GCP Cloud SQL databases to Cloud Storage buckets.

Denoising 7T Structural MRI with Conditional Generative Diffusion Models.