no code implementations • LREC 2022 • Farhad Akhbardeh, Marcos Zampieri, Cecilia Ovesdotter Alm, Travis Desell
Event identification in technical logbooks poses challenges given the limited logbook data available in specific technical domains, the large set of possible classes, and logbook entries typically being in short form and non-standard technical language.
no code implementations • 22 Oct 2024 • Zimeng Lyu, Amulya Saxena, Rohaan Nadeem, Hao Zhang, Travis Desell
RNNs are evolved independently for each stocks and portfolio trading decisions are made based on the predicted stock returns.
no code implementations • 19 Feb 2024 • Hitesh Vaidya, Travis Desell, Ankur Mali, Alexander Ororbia
The major challenge that makes crafting such a system difficult is known as catastrophic forgetting - an agent, such as one based on artificial neural networks (ANNs), struggles to retain previously acquired knowledge when learning from new samples.
no code implementations • 17 Feb 2024 • Zimeng Lyu, Pujan Thapa, Travis Desell
General aviation flight data for phase of flight identification is usually per-second data, comes on a large scale, and is class imbalanced.
no code implementations • 12 Jan 2024 • Zimeng Lyu, Alexander Ororbia, Rui Li, Travis Desell
In this work, we introduce a semi-supervised learning approach based on topological projections in self-organizing maps (SOMs), which significantly reduces the required number of labeled data points to perform parameter prediction, effectively exploiting information contained in large unlabeled datasets.
1 code implementation • 11 May 2023 • AbdElRahman ElSaid, Karl Ricanek, Zeming Lyu, Alexander Ororbia, Travis Desell
Continuous Ant-based Topology Search (CANTS) is a previously introduced novel nature-inspired neural architecture search (NAS) algorithm that is based on ant colony optimization (ACO).
no code implementations • 7 Mar 2023 • Hong Yang, William Gebhardt, Alexander G. Ororbia, Travis Desell
Out-of-distribution (OOD) inputs can compromise the performance and safety of real world machine learning systems.
no code implementations • 20 Feb 2023 • Zimeng Lyu, Alexander Ororbia, Travis Desell
Results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods, including online linear regression, fixed long short-term memory (LSTM) and gated recurrent unit (GRU) models trained online, as well as state-of-the-art, online ARIMA strategies.
1 code implementation • 13 Oct 2022 • Hong Yang, Travis Desell
To overcome this, we use the National General Aviation Flight Information Database (NGAFID), which contains flights recorded during regular operation of aircraft, and maintenance logs to construct a part failure dataset.
no code implementations • 21 Apr 2022 • Aizaz Ul Haq, Niranjana Deshpande, AbdElRahman ElSaid, Travis Desell, Daniel E. Krutz
Simulations using 52, 106 tactic records demonstrate that: I) eRNN is an effective prediction mechanism, II) TVA-E represents an improvement over existing state-of-the-art processes in accounting for tactic volatility, and III) Uncertainty reduction tactics are beneficial in accounting for tactic volatility.
no code implementations • 27 Feb 2022 • Zimeng Lyu, Travis Desell
Time series forecasting (TSF) is one of the most important tasks in data science, as accurate time series (TS) predictions can drive and advance a wide variety of domains including finance, transportation, health care, and power systems.
no code implementations • 27 Jan 2022 • Hong Yang, Travis Desell
We also show that augmentation improves accuracy for recurrent and self attention based architectures.
no code implementations • 9 Dec 2021 • Hitesh Vaidya, Travis Desell, Alexander Ororbia
A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data.
no code implementations • 7 Oct 2021 • Hong Yang, Aidan LaBella, Travis Desell
However, the development of such systems has been limited due to a lack of publicly labeled multivariate time series (MTS) sensor data.
no code implementations • ACL 2021 • Farhad Akhbardeh, Cecilia Ovesdotter Alm, Marcos Zampieri, Travis Desell
In this paper we focus on the problem of technical issue classification by considering logbook datasets from the automotive, aviation, and facilities maintenance domains.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Farhad Akhbardeh, Travis Desell, Marcos Zampieri
Processing maintenance logbook records is an important step in the development of predictive maintenance systems.
no code implementations • 21 Nov 2020 • AbdElRahman ElSaid, Joshua Karns, Zimeng Lyu, Alexander Ororbia, Travis Desell
This work introduces a novel, nature-inspired neural architecture search (NAS) algorithm based on ant colony optimization, Continuous Ant-based Neural Topology Search (CANTS), which utilizes synthetic ants that move over a continuous search space based on the density and distribution of pheromones, is strongly inspired by how ants move in the real world.
no code implementations • 21 Sep 2020 • Zimeng Lyu, AbdElRahman ElSaid, Joshua Karns, Mohamed Mkaouer, Travis Desell
Weight initialization is critical in being able to successfully train artificial neural networks (ANNs), and even more so for recurrent neural networks (RNNs) which can easily suffer from vanishing and exploding gradients.
no code implementations • 4 Jun 2020 • AbdElRahman ElSaid, Joshua Karns, Alexander Ororbia II, Daniel Krutz, Zimeng Lyu, Travis Desell
Transfer learning entails taking an artificial neural network (ANN) that is trained on a source dataset and adapting it to a new target dataset.
no code implementations • COLING 2020 • Farhad Akhbardeh, Travis Desell, Marcos Zampieri
Furthermore, it provides a way to encourage discussion on and sharing of new datasets and tools for logbook data analysis.
no code implementations • 15 May 2020 • Zimeng Lyu, Joshua Karns, AbdElRahman ElSaid, Travis Desell
This island based strategy is additionally compared to NEAT's (NeuroEvolution of Augmenting Topologies) speciation strategy.
no code implementations • 23 Apr 2020 • Jeffrey Palmerino, Qi Yu, Travis Desell, Daniel E. Krutz
Unfortunately, current self-adaptive approaches do not account for tactic volatility in their decision-making processes, and merely assume that tactics do not experience volatility.
1 code implementation • 6 Feb 2019 • Alexander Ororbia, Ahmed Ahmed Elsaid, Travis Desell
This paper presents a new algorithm, Evolutionary eXploration of Augmenting Memory Models (EXAMM), which is capable of evolving recurrent neural networks (RNNs) using a wide variety of memory structures, such as Delta-RNN, GRU, LSTM, MGU and UGRNN cells.
1 code implementation • 17 Nov 2018 • Travis Desell
This paper examines three generic strategies for improving the performance of neuro-evolution techniques aimed at evolving convolutional neural networks (CNNs).
no code implementations • 10 Oct 2017 • AbdElRahman ElSaid, Travis Desell, Fatima El Jamiy, James Higgins, Brandon Wild
This research improves the performance of the most effective LSTM network design proposed in the previous work by using a promising neuroevolution method based on ant colony optimization (ACO) to develop and enhance the LSTM cell structure of the network.
no code implementations • 15 Mar 2017 • Travis Desell
EXACT is in part modeled after the neuroevolution of augmenting topologies (NEAT) algorithm, with notable exceptions to allow it to scale to large scale distributed computing environments and evolve networks with convolutional filters.