no code implementations • 1 Dec 2023 • Alexander G. Ororbia
In this survey, we examine algorithms for conducting credit assignment in artificial neural networks that are inspired or motivated by neurobiology.
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.
1 code implementation • 3 Jun 2022 • Timothy Zee, Alexander G. Ororbia, Ankur Mali, Ifeoma Nwogu
While current deep learning algorithms have been successful for a wide variety of artificial intelligence (AI) tasks, including those involving structured image data, they present deep neurophysiological conceptual issues due to their reliance on the gradients that are computed by backpropagation of errors (backprop).
no code implementations • 24 Jun 2021 • Alexander G. Ororbia
In this article, we propose a novel form of unsupervised learning, continual competitive memory (CCM), as well as a computational framework to unify related neural models that operate under the principles of competition.
no code implementations • NLPerspectives (LREC) 2022 • Tharindu Cyril Weerasooriya, Alexander G. Ororbia, Christopher M. Homan
We propose a fully Bayesian framework for learning ground truth labels from noisy annotators.
no code implementations • 20 Nov 2019 • Ankur Mali, Alexander G. Ororbia, Clyde Lee Giles
For lossy image compression, we develop a neural-based system which learns a nonlinear estimator for decoding from quantized representations.
no code implementations • 26 Sep 2019 • AbdElRahman A. ElSaid, Alexander G. Ororbia, Travis J. Desell
Hand-crafting effective and efficient structures for recurrent neural networks (RNNs) is a difficult, expensive, and time-consuming process.
no code implementations • 20 Sep 2019 • Travis J. Desell, AbdElRahman A. ElSaid, Alexander G. Ororbia
EXAMM, in this study, was used to train over 10. 56 million RNNs in 5, 280 repeated experiments with varying components.
1 code implementation • CVPR 2019 • Anand Gopalakrishnan, Ankur Mali, Dan Kifer, C. Lee Giles, Alexander G. Ororbia
We propose novel neural temporal models for predicting and synthesizing human motion, achieving state-of-the-art in modeling long-term motion trajectories while being competitive with prior work in short-term prediction and requiring significantly less computation.
no code implementations • ACL 2019 • Alexander G. Ororbia, Ankur Mali, Matthew A. Kelly, David Reitter
We examine the benefits of visual context in training neural language models to perform next-word prediction.
no code implementations • 26 May 2018 • Alexander G. Ororbia, Ankur Mali
Finding biologically plausible alternatives to back-propagation of errors is a fundamentally important challenge in artificial neural network research.
no code implementations • 15 Mar 2018 • Alexander G. Ororbia, Ankur Mali, Jian Wu, Scott O'Connell, David Miller, C. Lee Giles
For lossy image compression systems, we develop an algorithm, iterative refinement, to improve the decoder's reconstruction compared to standard decoding techniques.
no code implementations • 5 Mar 2018 • Alexander G. Ororbia, Ankur Mali, Daniel Kifer, C. Lee Giles
Using back-propagation and its variants to train deep networks is often problematic for new users.