NeurIPS 2019: 33rd Conference on Neural Information Processing Systems
Dec
13
8:00 AM08:00

NeurIPS 2019: 33rd Conference on Neural Information Processing Systems

Presenting our paper with my co-authors at Beyond First Order Methods in ML workshop at the conference.

The title of the paper is: FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods. Nur Sila Gulgec (Lehigh University); Zheng Shi (Lehigh University); Neil Deshmukh (Moravian Academy); Shamim Pakzad (Lehigh University); Martin Takac (Lehigh University)

Higher-order methods, such as Newton, quasi-Newton and adaptive gradient descent methods, are extensively used in many scientific and engineering domains. At least in theory, these methods possess several nice features: they exploit local curvature information to mitigate the effects of ill-conditioning, they avoid or diminish the need for hyper-parameter tuning, and they have enough concurrency to take advantage of distributed computing environments. Researchers have even developed stochastic versions of higher-order methods, that feature speed and scalability by incorporating curvature information in an economical and judicious manner. However, often, higher-order methods are “undervalued.”

This workshop will attempt to shed light on this statement. Topics of interest include --but are not limited to-- second-order methods, adaptive gradient descent methods, regularization techniques, as well as techniques based on higher-order derivatives.

View Event →

Life Sciences Future - BioPharm: Scientific Presentation
Oct
3
7:30 AM07:30

Life Sciences Future - BioPharm: Scientific Presentation

Life Sciences Future - BioPharm is an event designed by Life Sciences PA to reflect the rapidly-evolving landscape in life sciences. This event is focused on timely topics in the biotechnology and pharmaceutical fields.

I will be presenting the latest updates to my research for an Adaptive, Low-Cost Device for Automated & Offline Medical Analysis Utilizing Neural Networks with Reinforcement Learning Optimization.

View Event →
Wills Eye Hospital - Birdshot Day
Sep
21
9:00 AM09:00

Wills Eye Hospital - Birdshot Day

Wills Eye Hospital - Birdshot Day

Wills Eye Hospital is a non-profit eye clinic and hospital in Philadelphia, Pennsylvania. It was established in 1832 and is the oldest continually operating eye-care facility in the United States.

The event is a patient advocacy and education event for those affected by Birdshot chorioretinopathy.

I will be speaking to introduce VocalEyes App and also about the latest AI-related research in Ophthalmology.

View Event →
PA STEAM Fest
Aug
31
11:00 AM11:00

PA STEAM Fest

The inaugural PA STEAM Fest 2019 focuses on a mix of Science, Technology, Engineering, Art, and Makers (STEAM), Electronic Entertainment, and Manufacturing & Production in a Steampunk theme. Founded by WeDiscoverGeeks in partnership with ArtsQuest. The event will promote programs and interests in these industries for families, digital educators, businesses, institutes, and everyone else interested in today’s modern culture and the historical evolution of Steampunk! This event includes workshops, lesson seminars, educational panels, new innovation, demos, digital artists, makers, geek entertainment, cosplay, and more!

I will be presenting “Delving into STEAM Education and AI”.

View Event →
MOPTA (Modeling and OPtimization: Theory and Application) 2019
Aug
14
3:00 PM15:00

MOPTA (Modeling and OPtimization: Theory and Application) 2019

MOPTA 2019 aims at bringing together a diverse group of people from both discrete and continuous optimization, working on both theoretical and applied aspects. There will be a small number of invited talks from distinguished speakers and contributed talks, spread over three days. The target is to present a diverse set of exciting new developments from different optimization areas while at the same time providing a setting which will allow increased interaction among the participants. Organizers aim to bring together researchers from both the theoretical and applied communities who do not usually have the chance to interact in the framework of a medium-scale event.

My presentation will focus on the isolation of the waveform data, the noise filtration via normalization, Butterworth and forward-backward filter application, and Fast Fourier transformation. It will also discuss one of the projects I worked on that has the trained Artificial Neural Network (ANN) contained 23 dense layers with the number of neurons decreasing per two layers with ReLU activation, how Multiclass activation was used along with AdamOptimizer.

View Event →