The Computational Learning, Intelligence and Perception Laboratory ClipLab

February 21, 2024

Our work on measures of divergence using representation entropy was accepted to ICASSP 2022. Congrats to Jhoan Keider and Oscar on their first publication in our lab. The pre print is available here: https://arxiv.org/abs/2112.01583

June 4, 2021

Our lab's PI has been awarded funding by the Department of Defense for a new project through its Defense Established Program to Stimulate Competitive Research (DEPSCoR) awards competition. Nathan Jacobs, associate professor in the Department of Computer Science, will serve as co-investigator and senior mentor.

This project will develop the theoretical foundations of alternative definitions of entropy and mutual information to address a fundamental problem in Machine Learning: building objective functions that can handle and integrate data from multiple sources with minimal supervision.

January 18, 2021

The CLIP Lab welcomes Santiago Posso Murillo and Jhoan Keider Hoyos Osorio to Lexington. Originally from Colombia, Santiago and Jhoan Keider will pursue MS and PhD degrees in Electrical Engineering at UK.
We are excited to having you here.

January 13, 2021

Nick's research will focus on developing a method of feature extraction using a novel definition of mutual information. This method will allow the construction of models with multiple levels of processing and nonlinearities and the untangling of feature dependencies.

January 5, 2020

Phillip will work on a mechanincal device to simulate the process of image acquisition performed by the eye, which combines information from the retina captured over time and eye motion processes. This device will be used to obtain data to test different algorithmic strategies for information extraction that combine visual and motor modalities.

1. Skean, Oscar, et al. "FroSSL: Frobenius Norm Minimization for Self-Supervised Learning." arXiv preprint arXiv:2310.02903 (2023).
2. Skean, Oscar, et al. "Dime: Maximizing mutual information by a difference of matrix-based entropies." arXiv preprint arXiv:2301.08164 (2023).
3. Hoyos-Osorio, Jhoan K., and Luis G. Sanchez-Giraldo. "The representation jensen-shannon divergence." arXiv preprint arXiv:2305.16446 (2023).

1. Posso Murillo, S., Skean, O., Sanchez Giraldo, L.G. "Non-uniform Sampling-Based Breast Cancer Classification," In: Cao, X., Xu, X., Rekik, I., Cui, Z., Ouyang, X. (eds) Machine Learning in Medical Imaging, MLMI 2023. Lecture Notes in Computer Science, 14349. Springer, Cham, 2023.
2. Eskandari, S., Lumpp, J., Sanchez Giraldo, L. "Skin Lesion Segmentation Improved by Transformer-Based Networks with Inter-scale Dependency Modeling." In: Cao, X., Xu, X., Rekik, I., Cui, Z., Ouyang, X. (eds) Machine Learning in Medical Imaging. MLMI 2023. Lecture Notes in Computer Science, 14348, Springer, Cham, 2023
3. Jhoan Keider Hoyos Osorio, Oscar Skean, Austin J. Brockmeier, and Luis Gonzalo Sanchez Giraldo, "The Representation Jensen-Rénji Divergence," To appear in International Conference on Acoustics, Speech and Signal Processing, 2022.
4. Shujian Yu, Luis Sanchez Giraldo, and José C. Príncipe, "Information-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities," International Joint Conference on Artificial Intelligence, 2021.

1. oshua Bowren, Luis Gonzalo Sanchez Giraldo, and Odelia Schwartz,  "Inference via Sparse Coding in a Hierarchical Vision Model," Journal of Vision, 22(19), 2022.
2. Yantao Wei, Shujian Yu, Luis Sanchez Giraldo, and Jose C. Principe, "Multiscale Principle of Relevant Information for Hyperspectral Image Classification," Machine Learning, Springer, 2021.
3. Md Nasir Uddin Laskar, Luis Gonzalo Sanchez Giraldo, Odelia Schwartz, "Deep Neural Networks capture texture sensitivity in V2," Journal of Vision, 2020.
4. Shujian Yu, Luis Gonzalo Sanchez Giraldo, Robert Jenssen, Jose C. Principe, "Multivariate Extension of Matrix-Based Rényi's alpha-Order Entropy Functional," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.

1. Austin J. Brockmeier, Claudio Cesar Claros-Olivares, Matthew Emigh, and Luis Gonzalo Sanchez Giraldo, "Identifying the Instances Associated with Distribution Shifts using the Max-Sliced Bures Divergence," NeurIPS 2021 Workshop DistShift, 2021.
2. Xu Pan, Elif Kartal, Luis Gonzalo Sanchez Giraldo, Odelia Schwartz,  "Brain-Inspired Weighted Normalization for CNN Image Classification," ICLR Workshop: How Can Findings About The Brain Improve AI Systems?, 2021.