As part of the quest to understand our reality, and understand how the world and our brain works, I am focused on the underlying mathematics and principles of intelligence and learning in Neural Networks.
B.Sc. in Computer Science at Sharif University of Technology
We are working on publishing a new method for Classifier-Free Guidance in Diffusion Models. We are working on generating high quality sample images that are consistent with given text prompts.
We worked on Expressive measures of graph similarity for ML tasks. Starting with non-parametric and kernel methods, and then incorporating deep parametric methods. Here I had the opportunity to introduce many ideas and theoretical analysis, create theoretical proofs and conduct benchmark experiments. I studied concepts in Geometric Deep Learning and Graph NNs, Approximation on Graphs, Graph Theory, Optimization and Topology.
We are experimenting with many aspects of Trustworthy ML on KANs, such as Robustness, Membership Inference, Certified Robustness. Collaborated with students at the University of Massachusetts
We studied and experimented on a model based on Markov Random Fields and Bayesian Inference, inspired by their use in computer vision tasks.