156 citations · 522 across the 37 of their papers we have counts for
3 papers · 1 filter
Reinforcement Learning with Subspaces using Free Energy Paradigm
Milad Ghorbani, Reshad Hosseini, Seyed Pooya Shariatpanahi +1
In large-scale problems, standard reinforcement learning algorithms suffer from slow learning speed. In this paper, we follow the framework of using subspaces to tackle this proble…
Contour Integration using Graph-Cut and Non-Classical Receptive Field
Zahra Mousavi Kouzehkanan, Reshad Hosseini, Babak Nadjar Araabi
Many edge and contour detection algorithms give a soft-value as an output and the final binary map is commonly obtained by applying an optimal threshold. In this paper, we propose…
FRMDN: Flow-based Recurrent Mixture Density Network
Seyedeh Fatemeh Razavi, Reshad Hosseini, Tina Behzad
The class of recurrent mixture density networks is an important class of probabilistic models used extensively in sequence modeling and sequence-to-sequence mapping applications. I…