Amir Samadi
PhD in Engineering
Amir.Samadi@warwick.ac.uk
+44 (0) 074 4382 5358
My supervisors are Prof. Mehrdad Dianati, Prof. Paul Jennings.
My research is sponsored by WMG.
Biography
About me
- I received my B.Sc. in Electrical Engineering-Digital Systems from the University of Tehran, Iran.
- I received my M.Sc. in Electrical Engineering-Control Systems from the Ferdowsi University of Mashhad, Iran.
GMy Research
The End-to-End (E2E) paradigm addresses driving tasks by generating desired outputs from sensory inputs through a single module using a deep learning method. The principal component of E2E Autonomous Vehicle (AV) systems, deep neural networks, decide inherently in a black-box manner. Even though the algorithm has a remarkable performance, there is no debugging and verification capability to fix faults and guarantee performance in all situations. The absence of intermediate outputs in the E2E method makes it untraceable to find the origin of the fault and explain how the E2E model reaches each decision. Therefore, this research aims to develop an interpretable E2E model particularly designed for automated driving. In my PhD, I attempt to investigate how to produce intermediate outputs within the E2E model to generate comprehensive explanations for different tasks of an AV.
Recent Publications
A. Samadi, M. F. Samadi, “Deep Fuzzy Neural Network: An Evolving Perspective,” in essential Guide to Fuzzy Systems, pp. Incorporated, Nova Science Publishers, 2019.
A. Samadi, H. Rafiei, and M. R. Akbarzadeh-T. "A Probabilistic Fuzzy Table Lookup Scheme with Negation Logic." In Recent Developments and the New Direction in Soft-Computing Foundations and Applications, pp. 161-171. Springer, Cham, 2021.
A. Samadi, M. Azizi, S. R. Kashef, M. R. Akbarzadeh-T, A. Akbarzadeh-T and A. Moradi, "Hand Prosthesis: Finger Localization Based on Forearm Ultrasound Imaging," 2019 7th International Conference on Robotics and Mechatronics (ICRoM), 2019, pp. 276-280, doi: 10.1109/ICRoM48714.2019.9071794.
E. Qasemi, A. Samadi, M. H. Shadmehr, B. Azizian, S. Mozaffari, A . Shirian and B. Alizadeh, “Highly Scalable, Shared Memory, Monte-Carlo Tree Search based Blokus Duo Solver on FPGA,” International Conference on Field-Programmable Technology (ICFPT), 2014, pp.370-373, IEEE.
A. Samadi, M. R. Akbarzdeh-T, “Z-number Restricted Boltzmann Machine,” 7th Iranian Joint Congress on Fuzzy and Intelligent Systems (CFIS), 2019.
H. Rafiei, A. Samadi, A. M. Naddaf, S. Naddaf, H. Hafiz, M. S. Abavisani, S. N. Golestani, A. R. AkbarzdehT, A. Moradi, M. Izadi, M. R. Akbarzdeh-T, “Magnet Tracking Based on Neural Network,” 7th Iranian Joint Congress on Fuzzy and Intelligent Systems (CFIS), 2019.