Elan Barenholtz, Ph.D.
Associate Professor Florida Atlantic University
- Boca Raton FL
Elan Barenholtz uses behavioral and embedded computational approaches to study the brain and behavior.
Multimedia
Social
Biography
Areas of Expertise
Education
Rutgers University
Ph.D.
Cognitive Science
2004
Affiliations
- Machine Perception and Cognitive Robotics (MPCR) Laboratory : Co-Director
- FAU’s Brain Institute (I-BRAIN) : Member
- NSF Panel : Reviewer
- Frontiers in Psychology : Editorial Board Member
Selected Media Appearances
FAU Awarded $2.4M NSF Grant to Train Data Scientist
Boca Raton Tribune online
2020-09-10
The project team includes Janet Robishaw, Ph.D., senior associate dean for research and chair, Department of Biomedical Science in FAU’s Schmidt College of Medicine, and an expert on genomic analysis; Ruth Tappen, Ed.D., Christine E. Lynn Eminent Scholar and Professor, FAU’s Christine E. Lynn College of Nursing, and an expert on nursing management and memory disorders; Taghi Khoshgoftaar, Ph.D., Motorola Professor in the Department of Computer and Electrical Engineering and Computer Science, and an expert on medical applications of big data analytics; Elan Barenholtz, Ph.D., an associate professor of psychology and more.
Could robots be psychology's new lab rats?
Science Magazine
2019-10-07
Sending a mouse through a maze can tell you a lot about how its little brain learns. But what if you could change the size and structure of its brain at will to study what makes different behaviors possible? That’s what Elan Barenholtz and William Hahn are proposing. The cognitive psychologist and computer scientist, both at Florida Atlantic University in Boca Raton, are running versions of classic psychology experiments on robots equipped with artificial intelligence. Their laptop-size robotic rovers can move and sense the environment through a camera. And they’re guided by computers running neural networks–models that bear some resemblance to the human brain...
FAU Robo-Pup Named Astro Described As ‘First Of Its Kind In The World’
CBS Miami
2019-09-25
“Just like a newborn baby learns how to speak and learns how to read your emotions, Astro has to learn that,” explains Elan Barenholtz, an associate professor in the FAU Department of Psychology. “So this new kind of artificual intelligence depends on a simulation of brain that’s actually living inside Astro.”...
Robotic Dog to Detect Weapons, Explosives
Asharq Al-awsat English
2019-08-20
Elan Barenholtz, co-developer of Astro, said the machine's key missions will include detecting guns, explosives and gun residue to assist police, the military, and security personnel. It will also be able to rapidly see and search thousands of faces in a database, smell the air to detect foreign substances, and hear and respond to distress calls that fall outside a human's audible hearing range...
Astro the dog-inspired quadruped robot can sit, lie down, and… learn?
Digital Trends
2019-08-15
“We honestly think Astro may be the coolest robot on the planet right now,” Elan Barenholtz, an associate professor in FAU’s Department of Psychology, told Digital Trends. “There is a lot of buzz in the community around the flexibility and robustness of quadruped robots. But other models out there don’t have a brain to match the sophistication of the body and mostly operate based on human remote control. What we are developing is a truly autonomous robotic ‘animal.’ Astro can see, hear and feel — and, in the near future, smell — using onboard sensors.”...
A Neuroscientist Explains Why Pokémon Go is Totally Messing Up Your Brain
LA Magazine
2016-07-28
At least that’s according to Elan Barenholtz, Ph.D., an associate professor in the Center for Complex Systems and Brain Sciences at Florida Atlantic University, who says that augmented and virtual reality games have created a “dangerous path” by offering a far more rewarding alternative to reality. “It’s doing something really that drugs do in that it’s artificially stimulating your reward centers,” says Barenholtz. “We’re messing around with giving ourselves stimulants and feedback that we’ve never encountered before. And just like drugs, you never know where this is going to go.”...
Selected Articles
Attention Restoration Through Virtual Environments
Journal of VisionM Islam, M Kleiman, E Barenholtz
2018
Comprehension of an audio versus an audiovisual lecture at 50% time-compression
Journal of VisionN Perez, M Kleiman, E Barenholtz
2018
Medicine Has Gone to the Dogs: Deep Learning and Robotic Olfaction to Mimic Working Dogs
IEEE Technology and Society MagazineE Stark, S Hoover, A DeCesare, E Barenholtz
2018
Canines and humans have coexisted for millennia, to our mutual benefit. Our estimated 35 000+ year history of coevolution, including selective breeding, has lead to the development of intimate forms of cooperation, perhaps unparalleled among mammalian species [26]. In addition to providing companionship, dogs can perform critical roles for humans, such as mental health support and aid for the disabled. Recent years have seen growth in the deployment of service dogs, which are trained to perform a specialized task to mitigate a disability, providing higher quality care, increased independence, and peace of mind for those with life-threatening illnesses.
Self-Organizing Map Methodology for Sorting Differential Expression Data of MMP-9 Inhibition
bioRxivRS Clair, M Teti, A Knapinska, G Fields, W Hahn, E Barenholtz
2019
An unsupervised machine-learning model, based on a self-organizing map (SOM), was employed to extract suggested target genes from DESeq2 differential expression analysis data. Such methodology was tested on matrixmetalloproteinase 9 (MMP9) inhibitors. The model generated information on several novel gene hits that may be regulated by MMP-9, suggesting the self-organizing map method may serve as a useful analytic tool in degradomics research for further differential expression data analysis. Original data was generated from a previous study, which consisted of quantitative measures in changes of levels of gene expression from 32,000 genes in four different conditions of stimulated T-cells treated with an MMP-9 inhibitor. Since intracellular target of MMP-9 are not yet well characterized, the functional enrichment analysis program, WebGestalt, was used for validation of the SOM identified regulated genes. The proposed data analysis method indicated MMP-99s prominent role in biological regulatory and metabolic processes as major categories of regulation of the predicted genes. Both fields suggest extensive intracellular targets for MMP-9-triggered regulation, which are new interests in MMP-9 research. The methodology presented here is useful for similar knowledge and discovery from quantitative datasets and a proposed extension of DESeq2 or similar data analysis.
Deep Learning Investigation of Mass Spectrometry Analysis from Melanoma Samples
IEEE International Symposium on Olfaction and Electronic Nose (ISOEN)EN Stark, JA Covington, S Agbroko, C Peng, WE Hahn, E Barenholtz
2019
Deep learning has yet to be widely applied in the field of chemical gas sensing, in part due to the nature of this data. Many applications of chemical gas sensing suffer from a limited number of samples of high dimensional data. In this study, a novel data approach is introduced to address these issues and is applied to a dataset from mass spectrometry (MS) for melanoma detection. Samples were taken from 32 patients presenting with a dermatological mole. Various data analyses were performed. Traditional analysis such as primary component analysis (PCA), linear discriminant analysis (LDA), and a perceptron were used. In addition, a 1-hidden layer, fully connected neural network (also known as a multilayer perceptron) and a deeper 5-hidden layer, fully connected neural network was trained to classify inputs as deriving from a melanoma or non-melanoma mole. We segmented each sample and trained the network to assign a probabilistic output interpreted as “confidence in melanoma” to each segment. Traditional inference testing on these confidence measures found highly significant differences in the outputs of the multilayer perceptrons between melanoma versus non-melanoma samples. This provides a statistically grounded approach to deep learning-based classification of small amounts of high dimensional data, given the ability to segment the samples into a sufficient number of inputs for model training.
