Search Results for author: Saeid Nahavandi

Found 39 papers, 8 papers with code

Improving MC-Dropout Uncertainty Estimates with Calibration Error-based Optimization

no code implementations7 Oct 2021 Afshar Shamsi, Hamzeh Asgharnezhad, Moloud Abdar, AmirReza Tajally, Abbas Khosravi, Saeid Nahavandi, Henry Leung

Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result.

MCUa: Multi-level Context and Uncertainty aware Dynamic Deep Ensemble for Breast Cancer Histology Image Classification

1 code implementation24 Aug 2021 Zakaria Senousy, Mohammed M. Abdelsamea, Mohamed Medhat Gaber, Moloud Abdar, U Rajendra Acharya, Abbas Khosravi, Saeid Nahavandi

It exploits the high sensitivity to the multi-level contextual information using an uncertainty quantification component to accomplish a novel dynamic ensemble model. MCUamodelhas achieved a high accuracy of 98. 11% on a breast cancer histology image dataset.

Breast Cancer Histology Image Classification Image Classification

Uncertainty-Aware Credit Card Fraud Detection Using Deep Learning

no code implementations28 Jul 2021 Maryam Habibpour, Hassan Gharoun, Mohammadreza Mehdipour, AmirReza Tajally, Hamzeh Asgharnezhad, Afshar Shamsi, Abbas Khosravi, Miadreza Shafie-khah, Saeid Nahavandi, Joao P. S. Catalao

Countless research works of deep neural networks (DNNs) in the task of credit card fraud detection have focused on improving the accuracy of point predictions and mitigating unwanted biases by building different network architectures or learning models.

Fraud Detection

An Uncertainty-Aware Deep Learning Framework for Defect Detection in Casting Products

no code implementations24 Jul 2021 Maryam Habibpour, Hassan Gharoun, AmirReza Tajally, Afshar Shamsi, Hamzeh Asgharnezhad, Abbas Khosravi, Saeid Nahavandi

Secondly, to achieve a reliable classification and to measure epistemic uncertainty, we employ an uncertainty quantification (UQ) technique (ensemble of MLP models) using features extracted from four pre-trained CNNs.

Defect Detection Image Classification +1

Confidence Aware Neural Networks for Skin Cancer Detection

no code implementations19 Jul 2021 Donya Khaledyan, AmirReza Tajally, Ali Sarkhosh, Afshar Shamsi, Hamzeh Asgharnezhad, Abbas Khosravi, Saeid Nahavandi

Deep learning (DL) models have received particular attention in medical imaging due to their promising pattern recognition capabilities.

Transfer Learning

Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods

no code implementations28 Apr 2021 Nooshin Ayoobi, Danial Sharifrazi, Roohallah Alizadehsani, Afshin Shoeibi, Juan M. Gorriz, Hossein Moosaei, Abbas Khosravi, Saeid Nahavandi, Abdoulmohammad Gholamzadeh Chofreh, Feybi Ariani Goni, Jiri Jaromir Klemes, Amir Mosavi

This study is novel as it carries out a comprehensive evaluation of the aforementioned three deep learning methods and their bidirectional extensions to perform prediction on COVID-19 new cases and new death rate time series.

Time Series Time Series Forecasting

SpinalNet: Deep Neural Network with Gradual Input

3 code implementations arXiv 2020 H M Dipu Kabir, Moloud Abdar, Seyed Mohammad Jafar Jalali, Abbas Khosravi, Amir F. Atiya, Saeid Nahavandi, Dipti Srinivasan

Traditional learning with ImageNet pre-trained initial weights and SpinalNet classification layers provided the SOTA performance on STL-10, Fruits 360, Bird225, and Caltech-101 datasets.

Fine-Grained Image Classification Transfer Learning

Review, Analysis and Design of a Comprehensive Deep Reinforcement Learning Framework

no code implementations27 Feb 2020 Ngoc Duy Nguyen, Thanh Thi Nguyen, Hai Nguyen, Doug Creighton, Saeid Nahavandi

However, development of a deep RL-based system is challenging because of various issues such as the selection of a suitable deep RL algorithm, its network configuration, training time, training methods, and so on.

A Visual Communication Map for Multi-Agent Deep Reinforcement Learning

no code implementations27 Feb 2020 Ngoc Duy Nguyen, Thanh Thi Nguyen, Doug Creighton, Saeid Nahavandi

In this paper, we have proposed a more scalable approach that not only deals with a great number of agents but also enables collaboration between dissimilar functional agents and compatibly combined with any deep reinforcement learning methods.

Optimal Uncertainty-guided Neural Network Training

no code implementations30 Dec 2019 H M Dipu Kabir, Abbas Khosravi, Abdollah Kavousi-Fard, Saeid Nahavandi, Dipti Srinivasan

Most of the existing cost functions of uncertainty guided NN training are not customizable and the convergence of training is uncertain.

Prediction Intervals

Deep Learning for Deepfakes Creation and Detection: A Survey

no code implementations25 Sep 2019 Thanh Thi Nguyen, Quoc Viet Hung Nguyen, Cuong M. Nguyen, Dung Nguyen, Duc Thanh Nguyen, Saeid Nahavandi

By reviewing the background of deepfakes and state-of-the-art deepfake detection methods, this study provides a comprehensive overview of deepfake techniques and facilitates the development of new and more robust methods to deal with the increasingly challenging deepfakes.

DeepFake Detection Face Swapping

Real-time Intent Prediction of Pedestrians for Autonomous Ground Vehicles via Spatio-Temporal DenseNet

no code implementations22 Apr 2019 Khaled Saleh, Mohammed Hossny, Saeid Nahavandi

We trained and evaluated our framework based on real data collected from urban traffic environments.

Realistic Hair Simulation Using Image Blending

no code implementations19 Apr 2019 Mohamed Attia, Mohammed Hossny, Saeid Nahavandi, Anousha Yazdabadi, Hamed Asadi

In this presented work, we propose a realistic hair simulator using image blending for dermoscopic images.

Data Augmentation

A New Tensioning Method using Deep Reinforcement Learning for Surgical Pattern Cutting

no code implementations10 Jan 2019 Thanh Thi Nguyen, Ngoc Duy Nguyen, Fernando Bello, Saeid Nahavandi

Surgeons normally need surgical scissors and tissue grippers to cut through a deformable surgical tissue.

Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications

1 code implementation31 Dec 2018 Thanh Thi Nguyen, Ngoc Duy Nguyen, Saeid Nahavandi

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems.

Decision Making Transfer Learning

Multi-Agent Deep Reinforcement Learning with Human Strategies

no code implementations12 Jun 2018 Thanh Nguyen, Ngoc Duy Nguyen, Saeid Nahavandi

In this paper, we introduce an approach that integrates human strategies to increase the exploration capacity of multiple deep reinforcement learning agents.

A Human Mixed Strategy Approach to Deep Reinforcement Learning

no code implementations5 Apr 2018 Ngoc Duy Nguyen, Saeid Nahavandi, Thanh Nguyen

In 2015, Google's DeepMind announced an advancement in creating an autonomous agent based on deep reinforcement learning (DRL) that could beat a professional player in a series of 49 Atari games.

Atari Games Efficient Exploration

A Multi-Objective Deep Reinforcement Learning Framework

no code implementations8 Mar 2018 Thanh Thi Nguyen, Ngoc Duy Nguyen, Peter Vamplew, Saeid Nahavandi, Richard Dazeley, Chee Peng Lim

This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks.

Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks

1 code implementation19 Sep 2016 Masoud Abdi, Saeid Nahavandi

We also demonstrate that our model outperforms very deep residual networks by 0. 22% (top-1 error) on the full ImageNet 2012 classification dataset.

Cannot find the paper you are looking for? You can Submit a new open access paper.