Publications

Results 26–50 of 73
Skip to search filters

Neurogenesis deep learning: Extending deep networks to accommodate new classes

Proceedings of the International Joint Conference on Neural Networks

Draelos, Timothy J.; Miner, Nadine E.; Lamb, Christopher L.; Cox, Jonathan A.; Vineyard, Craig M.; Carlson, Kristofor D.; Severa, William M.; James, Conrad D.; Aimone, James B.

Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing - data processing domains in which humans have long held clear advantages over conventional algorithms. In contrast to biological neural systems, which are capable of learning continuously, deep artificial networks have a limited ability for incorporating new information in an already trained network. As a result, methods for continuous learning are potentially highly impactful in enabling the application of deep networks to dynamic data sets. Here, inspired by the process of adult neurogenesis in the hippocampus, we explore the potential for adding new neurons to deep layers of artificial neural networks in order to facilitate their acquisition of novel information while preserving previously trained data representations. Our results on the MNIST handwritten digit dataset and the NIST SD 19 dataset, which includes lower and upper case letters and digits, demonstrate that neurogenesis is well suited for addressing the stability-plasticity dilemma that has long challenged adaptive machine learning algorithms.

More Details
TYPE Conference Poster YEAR 2017
ScopusOSTIDOI

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

Biologically Inspired Cognitive Architectures

James, Conrad D.; Aimone, James B.; Miner, Nadine E.; Vineyard, Craig M.; Rothganger, Fredrick R.; Carlson, Kristofor D.; Mulder, Samuel A.; Draelos, Timothy J.; Faust, Aleksandra; Marinella, Matthew J.; Naegle, John H.; Plimpton, Steven J.

Biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classes such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. In addition, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.

More Details
TYPE Journal Article YEAR 2017
ScopusOSTIDOI

A new method for producing automated seismic bulletins: Probabilistic event detection, association, and location

Bulletin of the Seismological Society of America

Draelos, Timothy J.; Ballard, Sanford B.; Young, Christopher J.; Brogan, Ronald

Given a set of observations within a specified time window, a fitness value is calculated at each grid node by summing station-specific conditional fitness values. Assuming each observation was generated by a refracted P wave, these values are proportional to the conditional probabilities that each observation was generated by a seismic event at the grid node. The node with highest fitness value is accepted as a hypothetical event location, subject to some minimal fitness value, and all arrivals within a longer time window consistent with that event are associated with it. During the association step, a variety of different phases are considered. Once associated with an event, an arrival is removed from further consideration. While unassociated arrivals remain, the search for other events is repeated until none are identified. Results are presented in comparison with analyst-reviewed bulletins for three datasets: a two-week ground-truth period, the Tohoku aftershock sequence, and the entire year of 2010. The probabilistic event detection, association, and location algorithm missed fewer events and generated fewer false events on all datasets compared to the associator used at the International Data Center (51% fewer missed and 52% fewer false events on the ground-truth dataset when using the same predictions).

More Details
TYPE Journal Article YEAR 2015
ScopusOSTIDOI
Results 26–50 of 73
Results 26–50 of 73