Farhad Pourkamali Anaraki

Assistant Professor, Department of Mathematical & Statistical Sciences

Director of Mathematics, Information, and Data Science (MINDS) Lab · University of Colorado Denver
Farhad portrait

Biography

Farhad Pourkamali is currently a tenure-track Assistant Professor in the Department of Mathematical and Statistical Sciences at the University of Colorado Denver (CU Denver). He earned his Ph.D. in Electrical Engineering from the University of Colorado Boulder (CU Boulder), where he subsequently completed a one-year postdoctoral fellowship in the Department of Applied Mathematics. Prior to his current role, he served as an Assistant Professor in the Computer Science Department at the University of Massachusetts Lowell (UMass Lowell) from 2018 to 2022. In 2021, he received the Visiting Faculty Research Program (VFRP) award from the Air Force Research Laboratory Information Directorate (AFRL/RI). Since the fall of 2022, he has been a part of CU Denver, where he leads the Mathematics, Information, and Data Science (MINDS) Lab. His main emphasis is on advancing machine learning techniques to reduce the necessity for human input, enhance their computational and statistical efficiency, and create accessible cyberinfrastructure resources. He is committed to addressing practical problems in various domains, including materials science and natural hazards analysis, and is actively seeking opportunities for collaboration.

Research Interests

The objective of my research is to advance the foundations and computational methods for building intelligent systems that can operate with minimal human supervision while understanding and quantifying their own uncertainty. By improving computational and data efficiency, developing novel approaches for calibrating and adapting pre-trained models, and applying these methods across domains from computer vision to scientific simulations, my work aims to create AI systems that are both high-performing and trustworthy. These AI models have been deployed in domains ranging from multiscale composite material modeling and additive manufacturing to remote sensing for environmental and geospatial applications.

Probabilistic Neural Networks

These models are designed to provide direct estimates about the variability in neural network outputs. For example, in regression settings, the model produces a parameterized predictive distribution, which can be used for uncertainty quantification. This is important because it enables more informed decision-making by explicitly modeling predictive confidence.

Model Calibration

I work on adapting calibration methods, such as temperature scaling and conformal prediction, to pre-trained vision and language models affected by domain shifts. Well-calibrated models produce reliable uncertainty estimates, which are critical for safe and trustworthy AI in high-stakes applications.

Multimodal Representation and Fusion

In many applications, data comes from multiple modalities such as text, images, and sensor measurements. Merging these in a probabilistic framework allows for consistent uncertainty estimates across modalities, leading to more robust and coherent predictions.

Model Reproducibility and Explainability

Training neural networks is inherently stochastic, leading to variability in results. Quantifying this training-induced variability is critical for scientific rigor. In addition, explainability methods help interpret model predictions, ensuring transparency and accountability.

Selected Publications

The complete collection of my publications can be found on Google Scholar.

Evaluation of Classification Models in Limited Data Scenarios with Application to Additive Manufacturing

Framework for unbiased test loss estimates with fewer labels in sparse-data regimes, reducing variance via adaptive sampling distribution.

Two-Stage Surrogate Modeling for Data-Driven Design Optimization with Application to Composite Microstructure Generation

Two-stage inverse design framework combining candidate narrowing with conformal inference filtering, validated on benchmarks and micromechanics case study.

Add another featured paper

Use this slot to feature a recent publication. Link to DOI/arXiv or your site.

Add a fourth featured paper

Brief 1–2 sentence highlight of contribution and results.

Grants

High-Throughput Design and Analysis of Novel Ceramics

Funding Agency: Army Research Lab (ARL)

Data Science Approaches to Advance High Solids Loading Additive Manufacturing

Funding Agency: Army Research Lab (ARL)

Multi-Scale Models based on Machine Learning and a Fiber Network Model

Funding Agency: National Aeronautics and Space Administration (NASA)

Learning from Imbalanced Data with Confidence and Minimal Supervision

Funding Agency: Air Force Research Laboratory Information Directorate (AFRL/RI)

Teaching

MATH 6388: Statistical and Machine Learning

Offered: Fall 2022, Fall 2023, Fall 2024

MATH 4/5388: Machine Learning Methods

Offered: Spring 2023 and Spring 2025

MATH 1376: Programming for Data Science

Offered: Spring 2024

MATH 5718: Applied Linear Algebra

Offered: Fall 2025

MATH 3382: Statistical Theory

Offered: Spring 2025

Next Course

Coming soon...

Lab Members

Matthew Knodell

Applied Math Ph.D. Student (2024–present)

Courtney Franzen

Applied Math Ph.D. Student (2024–present)

Rachel Drummond

Applied Math Ph.D. Student (2023–present)

Colin Furey

Applied Math Ph.D. Student (2023–present)