Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Learning Long-Term Dependencies in Irregularly-Sampled Time Series
This work designs a new algorithm based on the long short-term memory (LSTM) that separates its memory from its time-continuous state within the RNN, allowing it to respond to inputs arriving at arbitrary time-lags while ensuring a constant error propagation through the memory path.
An Automated Auto-encoder Correlation-based Health-Monitoring and Prognostic Method for Machine Bearings
This paper shows that AEC technique well-generalizes in several run-to-failure tests and demonstrates the superiority of the AEC over many other state-of-the-art approaches for the health monitoring and prognostic of machine bearings.
OpenWorm: overview and recent advances in integrative biological simulation of Caenorhabditis elegans
- G. Sarma, Chee Wai Lee, +16 authors S. Larson
- Engineering, MedicinePhilosophical Transactions of the Royal Society B
- 10 September 2018
An overview of the history and philosophy of OpenWorm is given, descriptions of the constituent sub-projects and corresponding open-science management practices are described, and current achievements of the project and future directions are discussed.
c302: a multiscale framework for modelling the nervous system of Caenorhabditis elegans
- P. Gleeson, David Lung, R. Grosu, Ramin M. Hasani, S. Larson
- Medicine, Computer SciencePhilosophical Transactions of the Royal Society B…
- 10 September 2018
A framework is developed that allows different instances of neuronal networks to be generated incorporating varying levels of anatomical and physiological detail, which can be investigated and refined independently or linked to other tools developed in the OpenWorm modelling toolchain.
Plug-and-Play Supervisory Control Using Muscle and Brain Signals for Real-Time Gesture and Error Detection
- Joseph DelPreto, A. F. Salazar-Gomez, Stephanie Gil, Ramin M. Hasani, F. Guenther, D. Rus
- Computer ScienceRobotics: Science and Systems
- 26 June 2018
This paper presents continuous classification of left and right hand-gestures using muscle signals, time-locked classification of error-related potentials using brain signals, and a framework that combines these pipelines to detect and correct robot mistakes during multiple-choice tasks.
Gershgorin Loss Stabilizes the Recurrent Neural Network Compartment of an End-to-end Robot Learning Scheme
- Mathias Lechner, Ramin M. Hasani, D. Rus, R. Grosu
- Computer ScienceIEEE International Conference on Robotics and…
- 1 May 2020
A new regularization loss component is introduced together with a learning algorithm that improves the stability of the learned autonomous system, by forcing the eigenvalues of the internal state updates of an LDS to be negative reals.
A novel Bayesian network-based fault prognostic method for semiconductor manufacturing process
- Guodong Wang, Ramin M. Hasani, Yungang Zhu, R. Grosu
- Computer Science, EngineeringIEEE International Conference on Industrial…
- 1 March 2017
A novel fault prognostic method based on Bayesian networks designed such that it can process both discrete and continuous variables, to represent the correlations between critical deviations and to process quality control data based on divide-and-conquer strategy is proposed.
GoTube: Scalable Stochastic Verification of Continuous-Depth Models
- Sophie Gruenbacher, Mathias Lechner, +4 authors R. Grosu
- Computer Science, MathematicsArXiv
- 18 July 2021
This work introduces a new stochastic verification algorithm that formally quantifies the behavioral robustness of any timecontinuous process formulated as a continuous-depth model and calls it GoTube, which is stable and sets the state of the art in terms of its ability to scale to time horizons well beyond what has been previously possible.
Neural circuit policies enabling auditable autonomy
- Mathias Lechner, Ramin M. Hasani, Alexander Amini, T. Henzinger, D. Rus, R. Grosu
- Computer Science
- 1 October 2020
It is discovered that a single algorithm with 19 control neurons, connecting 32 encapsulated input features to outputs by 253 synapses, learns to map high-dimensional inputs into steering commands, showing superior generalizability, interpretability and robustness compared with orders-of-magnitude larger black-box learning systems.
A generative neural network model for the quality prediction of work in progress products
- Guodong Wang, Anna Ledwoch, Ramin M. Hasani, R. Grosu, A. Brintrup
- Computer ScienceAppl. Soft Comput.
- 1 December 2019
A generative neural network model for automatically predicting work-in-progress product quality is proposed and the experimental results suggest that the method can precisely capture the defective products.