no code implementations • 6 Jan 2023 • Fateme Shahabi Nejad, Mohammad Mehdi Ebadzadeh
GANs are powerful generative models successfully applied in different areas but suffer from inherent challenges such as training instability and mode collapse.
1 code implementation • 24 Dec 2022 • Hamid Nasiri, Mohammad Mehdi Ebadzadeh
In the prediction and reconstruction phase, each of the IMFs is given to a separate MFRFNN for prediction, and predicted signals are summed to reconstruct the output.
1 code implementation • Neurocomputing 2022 • Hamid Nasiri, Mohammad Mehdi Ebadzadeh
MFRFNN consists of two fuzzy neural networks with Takagi-Sugeno-Kang fuzzy rules, one is used to produce the output, and the other to determine the system’s state.
no code implementations • 26 Oct 2021 • Sahar Roostaie, Mohammad Mehdi Ebadzadeh
Trust Region Policy Optimization (TRPO) is a popular and empirically successful policy search algorithm in reinforcement learning (RL).
no code implementations • 9 Aug 2021 • Shervin Halat, Mohammad Mehdi Ebadzadeh
Therefore, in this paper three modifications to the Double-DQN algorithm are proposed with the hope of maintaining the performance in the terms of both stability and overestimation.
no code implementations • 30 Jul 2021 • Alireza Nadali, Mohammad Mehdi Ebadzadeh
In recent years, there have been many deep structures for Reinforcement Learning, mainly for value function estimation and representations.
no code implementations • 4 Dec 2020 • Amir Aradnia, Maryam Amir Haeri, Mohammad Mehdi Ebadzadeh
These explicit feature maps enable us to access the data in the feature space explicitly and take advantage of K-means extensions in that space.
no code implementations • 25 Nov 2020 • Armin Salimi-Badr, Mohammad Mehdi Ebadzadeh
This learning approach does not require backpropagating the output error to learn the premise parts' parameters.
no code implementations • 1 Aug 2019 • Armin Salimi-Badr, Mohammad Mehdi Ebadzadeh
The proposed method is used to learn and reproduce different sequences simultaneously which is the novelty of this method.