cv

Senior Data Scientist

Vanguard

Developing AI algorithms to improve customer experience and reduce costs.

• NLP, ML, AI, AWS, Python, SQL

Director, Senior Research Scientist

University of Pennsylvania

Directed Neuroscience Laboratories, developing AI algorithms from primate visual circuitry.

• Primate Vision, Experimentation, AI, ML, Python, Matlab

Senior Research Scientist

Carnegie Mellon University

Developing AI algorithms from primate visual circuitry.

• Primate Vision, Experimentation, AI, ML, Python, Matlab

PhD

Wake Forest University

Neuroscience

TravNet

A computer vision project to automate sorting of neuron clusters - saving ~2 hours per day.

• CNNs
• DataWrangling

Document Scanner

A computer vision project to automate the identification of sensative financial documents.

• Multimodal Transformers
• AWS prod development

CSAT scanner

An NLP model using BeRT to cluster and estimate customer senitment using customer survey data

• BeRT Models
• NLP, Clustering

Statistical learning of visual transitions in monkey inferotemporal cortex

Proceedings of the National Academy of Sciences

One of the most fundamental functions of the brain is to predictupcoming events on the basis of the recent past. A closely relatedfunction is to signal when a prediction has been violated.

Neural Correlates of a Decision Variable Before Learning to Perform a Match/Non-Match Task

Journal of Neuroscience

The lateral prefrontal cortex plays an important role in working memory and decision-making, although little is known about how neuralcorrelates of these functions are shaped by learning. To understand the effect of learning on the neuronal representation of decision-making,werecordedsingleneuronsfromthelateralprefrontalcortexofmonkeysbeforeandaftertheyweretrainedtojudgewhethertwostimuli appeared at matching spatial locations.

Single-exposure visual memory judgments are reflected in inferotemporal cortex

eLife

Our visual memory percepts of whether we have encountered specific objects orscenes before are hypothesized to manifest as decrements in neural responses in inferotemporalcortex (IT) with stimulus repetition. To evaluate this proposal, we recorded IT neural responses astwo monkeys performed a single-exposure visual memory task designed to measure the rates offorgetting with time.

Differences in Intrinsic Functional Organization Between Dorsolateral Prefrontal and Posterior Parietal Cortex

Cerebral Cortex

The dorsolateral prefrontal and posterior parietal cortex are 2 com-ponents of the cortical network controlling attention, workingmemory, and executive function. Little is known about how the ana-tomical organization of the 2 areas accounts for their functionalspecialization

A software solution for the control of visual behavioral experimentation

Journal of Neuroscience Methods

Psychophysical and neurophysiological research requires precise control of experimental devices for the purpose of delivering stimuli andmonitoring behavioral and neural responses. This has previously been accomplished by complex, often proprietary, programmable systems,interfacing with a limited range of hardware.

Prediction suppression and surprise enhancement in monkey inferotemporal cortex

Journal of Neurophysiology

Exposing monkeys, over the course of daysand weeks, to pairs of images presented in fixed sequence, so that eachleading image becomes a predictor for the corresponding trailingimage, affects neuronal visual responsiveness in area TE. At the endof the training period, neurons respond relatively weakly to a trailingimage when it appears in a trained sequence and, thus, confirmsprediction, whereas they respond relatively strongly to the same imagewhen it appears in an untrained sequence and, thus, violates predic-tion.

Prediction suppression in monkey inferotemporal cortex depends on the conditional probability between images

Journal of Neurophysiology

When monkeysview two images in fixed sequence repeatedly over days and weeks,neurons in area TE of the inferotemporal cortex come to exhibitprediction suppression. The trailing image elicits only a weak re-sponse when presented following the leading image that preceded itduring training.

Population response magnitude variation in inferotemporal cortex predicts image memorability

eLife

Most accounts of image and object encoding in inferotemporal cortex (IT) focus on thedistinct patterns of spikes that different images evoke across the IT population. By analyzing datacollected from IT as monkeys performed a visual memory task, we demonstrate that variation in acomplementary coding scheme, the magnitude of the population response, can largely account forhow well images will be remembered.

Image familiarization sharpens response dynamics of neurons in inferotemporal cortex

Nature Neuroscience

Repeated viewing of an image over days and weeks induces a marked reduction in the strength with which neurons in monkey inferotemporal cortex respond to it. The processing advantage that attaches to this reduction is unknown.

Persistent Discharges in the Prefrontal Cortex of Monkeys Naive to Working Memory Tasks

Cerebral Cortex

Neurons in the prefrontal cortex and a network of interconnectedbrain areas discharge in a persistent fashion after the offset ofsensory stimulation. Such persistent discharges are thought toconstitute a neuronal correlate of working memory.

Pinpointing the neural signatures of single-exposure visual recognition memory

Proceedings of the National Academy of Sciences

Memories of the images that we have seen are thought to bereflected in the reduction of neural responses in high-level visualareas such as inferotemporal (IT) cortex, a phenomenon known asrepetition suppression (RS)

Changes in Prefrontal Neuronal Activity after Learning to Perform a Spatial Working Memory Task

Cerebral Cortex

The prefrontal cortex is considered essential for learning to performcognitive tasks though little is known about how the representationof stimulus properties is altered by learning. To address this issue,we recorded neuronal activity in monkeys before and after trainingon a task that required visual working memory.

Stimulus Selectivity in Dorsal and Ventral Prefrontal Cortex after Training in Working Memory Tasks

Journal of Neuroscience

The prefrontal cortex is known to represent different types of information in working memory. Contrasting theories propose that thedorsal and ventral regions of the lateral prefrontal cortex are innately specialized for the representation of spatial and nonspatialinformation, respectively (Goldman-Rakic, 1996), or that the two regions are shaped by the demands of cognitive tasks imposed on them(Miller, 2000)

Comparison of neural activity related to working memory in primate dorsolateral prefrontal and posterior parietal cortex

Frontiers in Systems Neuroscience

Neurons in a distributed network of cortical and subcortical areas continue to discharge after the presentation and disappearance of stimuli, providing a neural correlate for working memory. While it is thought that the prefrontal cortex plays a central role in this network, the relative contributions of other brain areas are not as well understood.