no code implementations • 30 Jan 2024 • Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
We assess the extent of LLM vulnerabilities, investigate emerging security and privacy attacks for LLMs, and review the potential defense mechanisms.
1 code implementation • 11 Nov 2023 • Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
Federated learning (FL) is gaining increasing popularity in the medical domain for analyzing medical images, which is considered an effective technique to safeguard sensitive patient data and comply with privacy regulations.
no code implementations • 24 Mar 2023 • Ervin Moore, Ahmed Imteaj, Shabnam Rezapour, M. Hadi Amini
Federated Learning (FL) has gained widespread popularity in recent years due to the fast booming of advanced machine learning and artificial intelligence along with emerging security and privacy threats.
1 code implementation • 28 May 2022 • Farid Ghareh Mohammadi, Cheng Chen, Farzan Shenavarmasouleh, M. Hadi Amini, Beshoy Morkos, Hamid R. Arabnia
Understanding 3D point cloud models for learning purposes has become an imperative challenge for real-world identification such as autonomous driving systems.
no code implementations • 6 Feb 2022 • Farid Ghareh Mohammadi, Farzan Shenavarmasouleh, Khaled Rasheed, Thiab Taha, M. Hadi Amini, Hamid R. Arabnia
In this study, we present our discovery of evolutionary and nature-inspired algorithms applications in Data Science and Data Analytics in three main topics of pre-processing, supervised algorithms, and unsupervised algorithms.
no code implementations • 15 Dec 2021 • Leila Zahedi, Farid Ghareh Mohammadi, M. Hadi Amini
OptABC integrates artificial bee colony algorithm, K-Means clustering, greedy algorithm, and opposition-based learning strategy for tuning the hyper-parameters of different machine learning models.
no code implementations • 12 Sep 2021 • Farid Ghareh Mohammadi, Farzan Shenavarmasouleh, M. Hadi Amini, Hamid R. Arabnia
Then, we offer a framework of these solutions, called universal smart cities decision making, with three main sections of data capturing, data analysis, and decision making to optimize the smart mobility within smart cities.
no code implementations • 11 Sep 2021 • Leila Zahedi, Farid Ghareh Mohammadi, M. Hadi Amini
In order to ensure the robustness of the proposed method, the algorithm takes a wide range of feasible hyper-parameter values, and is tested using a real-world educational dataset.
no code implementations • 22 Aug 2021 • Farzan Shenavarmasouleh, Farid Ghareh Mohammadi, M. Hadi Amini, Hamid R. Arabnia
Embodied AI aims to train an agent that can See (Computer Vision), Talk (NLP), Navigate and Interact with its environment (Reinforcement Learning), and Reason (General Intelligence), all at the same time.
no code implementations • 18 Aug 2021 • Farzan Shenavarmasouleh, Farid Ghareh Mohammadi, M. Hadi Amini, Thiab Taha, Khaled Rasheed, Hamid R. Arabnia
Medical Imaging is one of the growing fields in the world of computer vision.
no code implementations • 3 Jun 2021 • Luis Caicedo Torres, Luiz Manella Pereira, M. Hadi Amini
Then, we will follow up with a mathematical formulation and the prerequisites to understand OT.
1 code implementation • 29 Apr 2021 • Leila Zahedi, Farid Ghareh Mohammadi, Shabnam Rezapour, Matthew W. Ohland, M. Hadi Amini
In this paper, we examine the effectiveness of automated hyper-parameter tuning techniques to the realm of students' success.
no code implementations • 11 Jan 2021 • Ahmed Imteaj, M. Hadi Amini
Smartphones, autonomous vehicles, and the Internet-of-things (IoT) devices are considered the primary data source for a distributed network.
no code implementations • 1 Dec 2020 • Farid Ghareh Mohammadi, Farzan Shenavarmasouleh, M. Hadi Amini, Hamid R. Arabnia
However, the more universal an algorithm is, the higher number of feature dimensions it needs to work with, and that inevitably causes the emerging problem of Curse of Dimensionality (CoD).
no code implementations • 30 Nov 2020 • Farzan Shenavarmasouleh, Farid Ghareh Mohammadi, M. Hadi Amini, Hamid R. Arabnia
DRDr II is a hybrid of machine learning and deep learning worlds.
no code implementations • 25 Feb 2020 • Ahmed Imteaj, Urmish Thakker, Shiqiang Wang, Jian Li, M. Hadi Amini
Nowadays, devices are equipped with advanced sensors with higher processing/computing capabilities.
no code implementations • 11 Feb 2020 • Farid Ghareh Mohammadi, M. Hadi Amini, Hamid R. Arabnia
We also explore the effect of parameter tuning on performance of semantic auto-encoder (SAE).
no code implementations • 18 Nov 2019 • Ahmed Imteaj, M. Hadi Amini, Javad Mohammadi
This paper reintroduces the notion of resilience in the context of recent issues originated from climate change triggered events including severe hurricanes and wildfires.
no code implementations • 26 Aug 2019 • Farid Ghareh Mohammadi, M. Hadi Amini, Hamid R. Arabnia
In [1, 2], we have explored the theoretical aspects of feature extraction optimization processes for solving largescale problems and overcoming machine learning limitations.
no code implementations • 22 Aug 2019 • Farid Ghareh Mohammadi, M. Hadi Amini, Hamid R. Arabnia
Dimension reduction, together with EAs, lends itself to solve CoD and solve complex problems, in terms of time complexity, efficiently.
no code implementations • 16 Aug 2019 • Farid Ghareh Mohammadi, M. Hadi Amini, Hamid R. Arabnia
We focus on data science as a crucial area, specifically focusing on a curse of dimensionality (CoD) which is due to the large amount of generated/sensed/collected data.
no code implementations • 23 Jul 2019 • Farid Ghareh Mohammadi, Farzan Shenavarmasouleh, M. Hadi Amini, Hamid R. Arabnia
However, the increase in features leads to the problem of the curse of dimensionality (CoD), which is considered to be an NP-hard problem.