Alexander G. Ororbia II

Alexander G. Ororbia II
Assistant Professor
PhD, Information & Science Technology (The Pennsylvania State University), Minor in Social Data Analytics
B.S.E., Computer Science & Engineering (Bucknell University, U.S.A.), Minors in Mathematics & Philosophy
Director, Neural Adaptive Computing (NAC) Laboratory
Department of Computer Science
Rochester Institute of Technology (NY, USA)

Office: Golisano Hall Rm. 3537
Email: agovcs AT rit DOT edu (Teaching/Advising), ago AT cs DOT rit DOT edu

[ Home ] -- [ For Students ] -- [ Teaching ] -- [ Research ] -- [ Publications ] -- [ Talks ] -- [ Software ] -- [ The NAC Lab ] -- [ Academic Genealogy ]

Research Statement

The focus of my work is on neurocognitively-motivated inference and learning algorithms for artificial neural networks, with a focus on lifelong learning--an important and challenging open problem for machine learning. I study representation learning and draw insights from cognitive neuroscience to create intelligent systems that are ultimately meant to improve their performance in online, semi-supervised, real-world environments. Statistical learning programs today perform well on very constrained, narrowly-defined tasks but struggle and fail when required to extract/aggregate knowledge across multiple tasks (consisting of data from multiple modalities) and to deal with non-stationary, one-shot, and zero-shot learning environments. My mission is to develop the learning algorithms and computational models needed to create such general-purpose, adaptive agents and cognitive architectures.

It is the endeavor of my research group, the Neural Adaptive Computing (NAC) Laboratory, to synthesize key aspects of models of cognition and biological neuro-circuitry, as well as theories of mind and brain functionality, to construct new learning algorithms and architectures that generalize better to unseen data and continually adapt to novel situations. Ultimately, the hope is that by building lifelong learning machines, we might gain further insight into the workings of human intelligence itself.

Research Interests

Biologically-inspired learning algorithms, statistical learning procedures (especially for semi-supervised/stream-based/multi-modal learning)
Cognitive modeling and the design of neural-based cognitive architectures
Lifelong machine learning (LML), also referred to as never-ending learning, lifelong learning, and continual learning: See the lab page for further details
Artificial neural networks:
- Spiking neural networks, recurrent networks, competitive learning, neural memory models
- Neural probabilistic/generative models, particularly Boltzmann machines and variational autoencoders
Nature-inspired metaheuristic optimization, including ant colony optimization, particle swarm optimization, and neuro-evolution (differential evoluation and genetic algorithms)