4 citations · 10 across the 3 of their papers we have counts for
3 papers
eess.SP2018★ 4 cited
Anomaly Classification in Distribution Networks Using a Quotient Gradient System
Hamid Khodabandehlou, Iman Niazazari, Hanif Livani +1
The classification of anomalies or sudden changes in power networks versus normal abrupt changes or switching actions is essential to take appropriate maintenance actions that guar…
eess.SP2018★ 4 cited
Training Recurrent Neural Networks via Dynamical Trajectory-Based Optimization
Hamid Khodabandehlou, M. Sami Fadali
This paper introduces a new method to train recurrent neural networks using dynamical trajectory-based optimization. The optimization method utilizes a projected gradient system (P…
cs.LG2018★ 2 cited
Training Recurrent Neural Networks as a Constraint Satisfaction Problem
Hamid Khodabandehlou, M. Sami Fadali
This paper presents a new approach for training artificial neural networks using techniques for solving the constraint satisfaction problem (CSP). The quotient gradient system (QGS…