216 citations · 816 across the 46 of their papers we have counts for
14 papers · 1 filter
Cubature Kalman Filter Based Training of Hybrid Differential Equation Recurrent Neural Network Physiological Dynamic Models
Ahmet Demirkaya, Tales Imbiriba, Kyle Lockwood +5
Modeling biological dynamical systems is challenging due to the interdependence of different system components, some of which are not fully understood. To fill existing gaps in our…
Stochastic Mutual Information Gradient Estimation for Dimensionality Reduction Networks
Ozan Ozdenizci, Deniz Erdogmus
Feature ranking and selection is a widely used approach in various applications of supervised dimensionality reduction in discriminative machine learning. Nevertheless there exists…
NetCut: Real-Time DNN Inference Using Layer Removal
Mehrshad Zandigohar, Deniz Erdogmus, Gunar Schirner
Deep Learning plays a significant role in assisting humans in many aspects of their lives. As these networks tend to get deeper over time, they extract more features to increase ac…
Towards Creating a Deployable Grasp Type Probability Estimator for a Prosthetic Hand
Mehrshad Zandigohar, Mo Han, Deniz Erdogmus +1
For lower arm amputees, prosthetic hands promise to restore most of physical interaction capabilities. This requires to accurately predict hand gestures capable of grabbing varying…
Disentangled Adversarial Autoencoder for Subject-Invariant Physiological Feature Extraction
Mo Han, Ozan Ozdenizci, Ye Wang +2
Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner. One major challenge of…
Stopping Criterion Design for Recursive Bayesian Classification: Analysis and Decision Geometry
Aziz Kocanaogullari, Murat Akcakaya, Deniz Erdogmus
Systems that are based on recursive Bayesian updates for classification limit the cost of evidence collection through certain stopping/termination criteria and accordingly enforce…
AutoBayes: Automated Bayesian Graph Exploration for Nuisance-Robust Inference
Andac Demir, Toshiaki Koike-Akino, Ye Wang +1
Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning. We introduce an automated Ba…
Active recursive Bayesian inference using Rényi information measures
Yeganeh M. Marghi, Aziz Kocanaogullari, Murat Akcakaya +1
Recursive Bayesian inference (RBI) provides optimal Bayesian latent variable estimates in real-time settings with streaming noisy observations. Active RBI attempts to effectively s…
Mapping Motor Cortex Stimulation to Muscle Responses: A Deep Neural Network Modeling Approach
Md Navid Akbar, Mathew Yarossi, Marc Martinez-Gost +6
A deep neural network (DNN) that can reliably model muscle responses from corresponding brain stimulation has the potential to increase knowledge of coordinated motor control for n…
Information Theoretic Feature Transformation Learning for Brain Interfaces
Ozan Ozdenizci, Deniz Erdogmus
Objective: A variety of pattern analysis techniques for model training in brain interfaces exploit neural feature dimensionality reduction based on feature ranking and selection he…
Adversarial Deep Learning in EEG Biometrics
Ozan Ozdenizci, Ye Wang, Toshiaki Koike-Akino +1
Deep learning methods for person identification based on electroencephalographic (EEG) brain activity encounters the problem of exploiting the temporally correlated structures or r…
Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders
Ozan Ozdenizci, Ye Wang, Toshiaki Koike-Akino +1
We introduce adversarial neural networks for representation learning as a novel approach to transfer learning in brain-computer interfaces (BCIs). The proposed approach aims to lea…
Structured Adversarial Attack: Towards General Implementation and Better Interpretability
Kaidi Xu, Sijia Liu, Pu Zhao +6
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and a…
Invariant Representations from Adversarially Censored Autoencoders
Ye Wang, Toshiaki Koike-Akino, Deniz Erdogmus
We combine conditional variational autoencoders (VAE) with adversarial censoring in order to learn invariant representations that are disentangled from nuisance/sensitive variation…