I am currently a PhD candidate at the Center for Complex Systems and Brain Sciences in the Cognitive Neurodynamics laboratory. I hold a BS in mathematics, a BA in philosophy and an MS in computer science. The long-term aim of my project is to develop a brain-computer-interface (BCI) to improve working memory (WM) function, e.g. in those afflicted with dementias such as Alzheimer’s. WM is a memory subsystem that contains internal representations of recent events for a pending action. BCIs are neural engineering devices that restore or improve natural central nervous system (CNS) output (Wolpaw & Wolpaw, 2012). They record signals from the brain, extract signal features, and translate those features to commands which are then used to actively perturb, or passively monitor, the CNS. There are currently no BCIs that improve working memory (WM). The first step in creating a BCI to improve human working memory is to identify WM’s relevant features in primate brain activity. The second step is to confirm the results from primates in the human EEG. This will enable feature extraction for human BCI applications such as WM training, neurofeedback, and transcranial magnetic stimulation.
I have a Masters in Medical Sciences in Neuroscience & Aging as well as a BS in Psychology with a minor in Human Integrated Biology. Within the Cognitive Neurodynamics laboratory, I'm using human fMRI data to model the large scale network of working memory. Currently I'm investigating various node localization techniques to identify how different node definitions yield different networks. Future research will focus on applying machine learning algorithms and directed functional connectivity analysis of said working memory network.
I study functional brain networks involved in the processing the emotional content of facial and vocal expressions. I am interested in how these networks may differ between clinically normal individuals and those with deficits in this type of processing, such as individuals with an autism spectrum disorder (ASD). I plan to use functional imaging methods to elucidate these differences. I have further interest in other sensory processing areas, such as the perception of pitch and music, and have worked in the past on projects related to human evolution, including human brain evolution.
I received my Bachelor’s degree in Computer Science in May 2016, and have been a researcher in the MPCR lab since November 2015. I work with Dr. Elan Barenholtz using deep learning to help solve problems in computational biology. I believe that neural-inspired machine learning techniques are increasingly capable of modelling biological interactions. My goal as a PhD student is to design computer models which can both be used as predictive tools, and reverse-engineered to further our understanding of biology. With the MPCR lab, I designed and implemented a highly accurate, interpretable deep learning tool for early lung, brain, and kidney cancer detection using targeted RNA-Seq data which can be analyzed to find new biomarkers for cancer. I am currently interested in developing algorithms to understand protein folding and molecular interaction in order to assist in designer molecule creation.
I competed my Bachelor's Degree in Chemistry and Psychology and my MA in cognitive Psychology. I am currently working with Dr Summer Sheremata. I am interested in human visual working memory and its neural basis. Currently my study is focusing on the individual difference in working memory capacity and how it leads to different processes.
I study targeted gene therapy to stop neovascularization in the eye for diseases such as AMD and diabetic retinopathy. I currently use animal models to study these therapies.
Michael joined the MPCR lab in February 2015 and received his undergraduate degree in Biology from Florida Atlantic University in August 2016. Before joining the MPCR lab, he modeled the propagation of invasive species throughout Lake Okeechobee and the Florida Everglades in the FAU Geoscience Department. He has since combined cutting edge, neurally-inspired methods in machine learning with his knowledge of remote sensing and GIS to create new ways to solve geospatial problems, such as land cover classification of aerial photographs and autonomous tracking of animal species using drones. Besides working on novel applications for machine learning algorithms, he has also worked to develop new algorithms in the areas of sparse coding, compressive sensing, and locally-competitive neural networks. He believes machines can do anything and is also the CTO of VoxelRx, LLC, an offshoot of the lab dedicated to performing medical imaging using machine learning.