129 citations · 717 across the 46 of their papers we have counts for
5 papers · 1 filter
Training-free Neural Architecture Search for RNNs and Transformers
Aaron Serianni, Jugal Kalita
Neural architecture search (NAS) has allowed for the automatic creation of new and effective neural network architectures, offering an alternative to the laborious process of manua…
Spatiotemporal Transformer for Stock Movement Prediction
Daniel Boyle, Jugal Kalita
Financial markets are an intriguing place that offer investors the potential to gain large profits if timed correctly. Unfortunately, the dynamic, non-linear nature of financial ma…
Utilizing Priming to Identify Optimal Class Ordering to Alleviate Catastrophic Forgetting
Gabriel Mantione-Holmes, Justin Leo, Jugal Kalita
In order for artificial neural networks to begin accurately mimicking biological ones, they must be able to adapt to new exigencies without forgetting what they have learned from p…
Incremental Deep Neural Network Learning using Classification Confidence Thresholding
Justin Leo, Jugal Kalita
Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only…
Moving Towards Open Set Incremental Learning: Readily Discovering New Authors
Justin Leo, Jugal Kalita
The classification of textual data often yields important information. Most classifiers work in a closed world setting where the classifier is trained on a known corpus, and then i…