| 1. |
- Beikmohammadi, Ali, 1995-, et al.
(författare)
-
SWP-LeafNET : A novel multistage approach for plant leaf identification based on deep CNN
- 2022
-
Ingår i: Expert systems with applications. - : Elsevier BV. - 0957-4174 .- 1873-6793. ; 202
-
Tidskriftsartikel (refereegranskat)abstract
- Modern scientific and technological advances allow botanists to use computer vision-based approaches for plant identification tasks. These approaches have their own challenges. Leaf classification is a computer-vision task performed for the automated identification of plant species, a serious challenge due to variations in leaf morphology, including its size, texture, shape, and venation. Researchers have recently become more inclined toward deep learning-based methods rather than conventional feature-based methods due to the popularity and successful implementation of deep learning methods in image analysis, object recognition, and speech recognition.In this paper, to have an interpretable and reliable system, a botanist’s behavior is modeled in leaf identification by proposing a highly-efficient method of maximum behavioral resemblance developed through three deep learning-based models. Different layers of the three models are visualized to ensure that the botanist’s behavior is modeled accurately. The first and second models are designed from scratch. Regarding the third model, the pre-trained architecture MobileNetV2 is employed along with the transfer-learning technique. The proposed method is evaluated on two well-known datasets: Flavia and MalayaKew. According to a comparative analysis, the suggested approach is more accurate than hand-crafted feature extraction methods and other deep learning techniques in terms of 99.67% and 99.81% accuracy. Unlike conventional techniques that have their own specific complexities and depend on datasets, the proposed method requires no hand-crafted feature extraction. Also, it increases accuracy as compared with other deep learning techniques. Moreover, SWP-LeafNET is distributable and considerably faster than other methods because of using shallower models with fewer parameters asynchronously.
|
|
| 2. |
- Beikmohammadi, Ali, 1995-, et al.
(författare)
-
Accelerating actor-critic-based algorithms via pseudo-labels derived from prior knowledge
- 2024
-
Ingår i: Information Sciences. - 0020-0255 .- 1872-6291. ; 661
-
Tidskriftsartikel (refereegranskat)abstract
- Despite the huge success of reinforcement learning (RL) in solving many difficult problems, its Achilles heel has always been sample inefficiency. On the other hand, in RL, taking advantage of prior knowledge, intentionally or unintentionally, has usually been avoided, so that, training an agent from scratch is common. This not only causes sample inefficiency but also endangers safety –especially during exploration. In this paper, we help the agent learn from the environment by using the pre-existing (but not necessarily exact or complete) solution for a task. Our proposed method can be integrated with any RL algorithm developed based on policy gradient and actor-critic methods. The results on five tasks with different difficulty levels by using two well-known actor-critic-based methods as the backbone of our proposed method (SAC and TD3) show our success in greatly improving sample efficiency and final performance. We have gained these results alongside robustness to noisy environments at the cost of just a slight computational overhead, which is negligible.
|
|
| 3. |
- Beikmohammadi, Ali, 1995-, et al.
(författare)
-
Comparing NARS and Reinforcement Learning : An Analysis of ONA and Q-Learning Algorithms
- 2023
-
Ingår i: Artificial General Intelligence. - : Springer. - 9783031334696 - 9783031334689 ; , s. 21-31
-
Konferensbidrag (refereegranskat)abstract
- In recent years, reinforcement learning (RL) has emerged as a popular approach for solving sequence-based tasks in machine learning. However, finding suitable alternatives to RL remains an exciting and innovative research area. One such alternative that has garnered attention is the Non-Axiomatic Reasoning System (NARS), which is a general-purpose cognitive reasoning framework. In this paper, we delve into the potential of NARS as a substitute for RL in solving sequence-based tasks. To investigate this, we conduct a comparative analysis of the performance of ONA as an implementation of NARS and Q-Learning in various environments that were created using the Open AI gym. The environments have different difficulty levels, ranging from simple to complex. Our results demonstrate that NARS is a promising alternative to RL, with competitive performance in diverse environments, particularly in non-deterministic ones.
|
|
| 4. |
- Beikmohammadi, Ali, 1995-, et al.
(författare)
-
Compressed Federated Reinforcement Learning with a Generative Model
- 2024
-
Ingår i: Machine Learning and Knowledge Discovery in Databases. Research Track. - : Springer. - 9783031703591 - 9783031703584 ; , s. 20-37
-
Konferensbidrag (refereegranskat)abstract
- Reinforcement learning has recently gained unprecedented popularity, yet it still grapples with sample inefficiency. Addressing this challenge, federated reinforcement learning (FedRL) has emerged, wherein agents collaboratively learn a single policy by aggregating local estimations. However, this aggregation step incurs significant communication costs. In this paper, we propose CompFedRL, a communication-efficient FedRL approach incorporating both \textit{periodic aggregation} and (direct/error-feedback) compression mechanisms. Specifically, we consider compressed federated Q-learning with a generative model setup, where a central server learns an optimal Q-function by periodically aggregating compressed Q-estimates from local agents. For the first time, we characterize the impact of these two mechanisms (which have remained elusive) by providing a finite-time analysis of our algorithm, demonstrating strong convergence behaviors when utilizing either direct or error-feedback compression. Our bounds indicate improved solution accuracy concerning the number of agents and other federated hyperparameters while simultaneously reducing communication costs. To corroborate our theory, we also conduct in-depth numerical experiments to verify our findings, considering Top-K and Sparsified-K sparsification operators.
|
|
| 5. |
- Beikmohammadi, Ali, 1995-, et al.
(författare)
-
On the Convergence of Federated Learning Algorithms Without Data Similarity
- 2024
-
Ingår i: IEEE Transactions on Big Data. - 2332-7790.
-
Tidskriftsartikel (refereegranskat)abstract
- Data similarity assumptions have traditionally been relied upon to understand the convergence behaviors of federated learning methods. Unfortunately, this approach often demands fine-tuning step sizes based on the level of data similarity. When data similarity is low, these small step sizes result in an unacceptably slow convergence speed for federated methods. In this paper, we present a novel and unified framework for analyzing the convergence of federated learning algorithms without the need for data similarity conditions. Our analysis centers on an inequality that captures the influence of step sizes on algorithmic convergence performance. By applying our theorems to well-known federated algorithms, we derive precise expressions for three widely used step size schedules: fixed, diminishing, and step-decay step sizes, which are independent of data similarity conditions. Finally, we conduct comprehensive evaluations of the performance of these federated learning algorithms, employing the proposed step size strategies to train deep neural network models on benchmark datasets under varying data similarity conditions. Our findings demonstrate significant improvements in convergence speed and overall performance, marking a substantial advancement in federated learning research.
|
|
| 6. |
- Beikmohammadi, Ali, 1995-, et al.
(författare)
-
TA-Explore : Teacher-Assisted Exploration for Facilitating Fast Reinforcement Learning: Extended Abstract
- 2023
-
Ingår i: AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. - : The International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). - 9781450394321 ; , s. 2412-2414
-
Konferensbidrag (refereegranskat)abstract
- Reinforcement Learning (RL) is crucial for data-driven decision-making but suffers from sample inefficiency. This poses a risk to system safety and can be costly in real-world environments with physical interactions. This paper proposes a human-inspired framework to improve the sample efficiency of RL algorithms, which gradually provides the learning agent with simpler but similar tasks that progress toward the main task. The proposed method does not require pre-training and can be applied to any goal, environment, and RL algorithm, including value-based and policy-based methods, as well as tabular and deep-RL methods. The framework is evaluated on a Random Walk and optimal control problem with constraint, showing good performance in improving the sample efficiency of RL-learning algorithms.
|
|
| 7. |
- Imani, Mehdi, et al.
(författare)
-
The Impact of SMOTE and ADASYN on Random Forest and Advanced Gradient Boosting Techniques in Telecom Customer Churn Prediction
- 2024
-
Ingår i: 2024 10th International Conference on Web Research (ICWR). - : IEEE (Institute of Electrical and Electronics Engineers). - 9798350394986 ; , s. 202-209
-
Konferensbidrag (refereegranskat)abstract
- This paper explores the capability of various machine learning algorithms, including Random Forest and advanced gradient boosting techniques such as XGBoost, LightGBM, and CatBoost, to predict customer churn in the telecommunications sector. For this analysis, a dataset available to the public was employed. The performance of these algorithms was assessed using recognized metrics, including Accuracy, Precision, Recall, F1-score, and the Receiver Operating Characteristic Area Under Curve (ROC AUC). These metrics were evaluated at different phases: subsequent to data preprocessing and feature selection; following the application of SMOTE and ADASYN sampling methods; and after conducting hyperparameter tuning on the data that had been adjusted by SMOTE and ADASYN.The outcomes underscore the notable efficiency of upsampling techniques such as SMOTE and ADASYN in addressing the imbalance inherent in customer churn prediction. Notably, the application of random grid search for hyperparameter optimization did not significantly alter the results, which remained comparatively unchanged. The algorithms' performance post-ADASYN application marginally surpassed that observed after SMOTE application. Remarkably, LightGBM achieved an exceptional F1-score of 89% and an ROC AUC of 95% subsequent to the ADASYN sampling technique. This underlines the effectiveness of advanced boosting algorithms and upsampling methods like SMOTE and ADASYN in navigating the complexities of imbalanced datasets and intricate feature interdependencies.
|
|
