Education

  • Doctor of Philosophy (Ph.D.) in Electrical and Computer Engineering
    Majoring in Artificial Intelligence and Machine Learning".
    Rowan University
    New Jersey, USA
  • Master of Science (M.S.) in Computer Science
    COMSATS University Islamabad
    Islamabad, Pakistan

Experiences

  • Post Doctoral Scholar
    I am Working at the intersection of artificial intelligence and digital pathology to conduct innovative research that helps early cancer diagnosis, prognosis, treatment response prediction, and biomarker discovery—ultimately improving patient outcomes and survival rates.
    The Ohio State University Wexner Medical Center
    Columbus, OH
  • Large Language Model (LLM) Researher
    1). Focused on deep learning, graph neural networks, NLP, medical foundation models, and large language models in healthcare. 2). Conducted hands-on research, applying academic knowledge to challenges like automating medical coding in medical billing. 3). Advanced my expertise in AI for healthcare and contributed to AI-driven automation in healthcare.
    St. John's University
    Queens, NY
  • Artificial Intelligence Engineer
    I worked as an artificial intelligence engineer with IBIS Corp, a New Jersey company specializing in cloud-based medical image data management. I had the opportunity to work on a project that focused on detecting and redacting a patient's identifying/health information (PII/PHI) within multiple medical imaging data (i.e., DICOM, MRI, CT scans, and WSI across all modalities and physicians' notes) to ensure that large-scale medical data can be made available for the research community without leakage of the critical patient’s (PII/PHI) information. In this role, I had the opportunity to research and develop the entire end-to-end deep learning pipeline solely, contributing to the successful National Institute of Health (NIH) SBIR Phase I contract.
    IBIS Inc.
    Princeton, NJ

Last publications

  • Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning

    Authors: Hikmat Khan

    IEEE International Joint Conference on Neural Networks (IJCNN) • 2024

    Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic forgetting. However, these approaches suffer from a problem called "rehearsal memory overfitting, " where the model becomes too specialized on limited memory samples and loses its ability to generalize effectively. As a result, the effectiveness of the rehearsal memory progressively decays, ultimately resulting in catastrophic forgetting of the learned tasks. We introduce the Adversarially Diversified Rehearsal Memory (ADRM) to address the memory overfitting challenge. This novel method is designed to enrich memory sample diversity and bolster resistance against natural and adversarial noise disruptions. ADRM employs the FGSM attacks to introduce adversarially modified memory samples, achieving two primary objectives: enhancing memory diversity and fostering a robust response to continual feature drifts in memory samples. Our contributions are as follows: Firstly, ADRM addresses overfitting in rehearsal memory by employing FGSM to diversify and increase the complexity of the memory buffer. Secondly, we demonstrate that ADRM mitigates memory overfitting and significantly improves the robustness of CL models, which is crucial for safety-critical applications. Finally, our detailed analysis of features and visualization demonstrates that ADRM mitigates feature drifts in CL memory samples, significantly reducing catastrophic forgetting and resulting in a more resilient CL model. Additionally, our in-depth t-SNE visualizations of feature distribution and the quantification of the feature similarity further enrich our understanding of feature representation in existing CL approaches.

Skills

Pytorch

Tensor Flow