Mark Crowley

Site being updated, see my Research Lab page for current information.

My research seeks dependable and transparent ways to augment human decision making in complex domains in the presence of spatial structure, large scale streaming data, or uncertainty. My focus is on developing new algorithms within the fields of Reinforcement Learning, Deep Learning and Ensemble Methods. I often work in collaboration with researchers in applied fields such as sustainable forest management, computational sustainability, ecology, autonomous driving, physical chemistry and medical imaging.

Note for Potential Graudate Students

As of Sept 28, 2020 I have enough graduate students and I am not accepting new applications. Good luck with your search though.

Writing

Besides my publications, you can follow my Computationally Thinking blog or @compthink on twitter for links and thoughts on Artificial Intellgience, Machine Learning and how technology and science are advancing.

news

Apr 16, 2021	First news post, new website up and running... more: First news post

selected publications

Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem

Sikaroudi, Milad, Ghojogh, Benyamin, Karray, Fakhri, Crowley, Mark, and Tizhoosh, H. R.

In 25th International Conference on Pattern Recognition (ICPR) 2021

Abs arXiv PDF

Variants of Triplet networks are robust entities for learning a discriminative embedding subspace. There exist different triplet mining approaches for selecting the most suitable training triplets. Some of these mining methods rely on the extreme distances between instances, and some others make use of sampling. However, sampling from stochastic distributions of data rather than sampling merely from the existing embedding instances can provide more discriminative information. In this work, we sample triplets from distributions of data rather than from existing instances. We consider a multivariate normal distribution for the embedding of each class. Using Bayesian updating and conjugate priors, we update the distributions of classes dynamically by receiving the new mini-batches of training data. The proposed triplet mining with Bayesian updating can be used with any triplet-based loss function, e.g., triplet-loss or Neighborhood Component Analysis (NCA) loss. Accordingly, Our triplet mining approaches are called Bayesian Updating Triplet (BUT) and Bayesian Updating NCA (BUNCA), depending on which loss function is being used. Experimental results on two public datasets, namely MNIST and histopathology colorectal cancer (CRC), substantiate the effectiveness of the proposed triplet mining method.
Isolation Mondrian Forest for Batch and Online Anomaly Detection

Ma, Haoran, Ghojogh, Benyamin, Samad, Maria N, Zheng, Dongyu, and Crowley, Mark

In IEEE International Conference on Systems, Man, and Cybernetics (IEEE-SMC-2020) 2020
A review of machine learning applications in wildfire science and management

Jain, Piyush, Coogan, Sean CP, Ganapathi Subramanian, Sriram, Crowley, Mark, Taylor, Steve, and Flannigan, Mike D

Environmental Reviews 2020

arXiv PDF
Distributed Nonlinear Model Predictive Control and Metric Learning for Heterogeneous Vehicle Platooning with Cut-in/Cut-out Maneuvers

Basiri, Mohammad Hossein, Ghojogh, Benyamin, Azad, Nasser L, Fischmeister, Sebastian, Karray, Fakhri, and Crowley, Mark

In Proceeding of the 59th IEEE Conference on Decision and Control (CDC-2020) 2020
AI Education Through Real World Problems

Crowley, Mark

In The Seventh Symposium on Educational Advances in Artificial Intellgience. 2017

Tweets by compthink