突触记忆巩固已被认为是支持神经形态人工智能（AI）系统中持续学习的关键机制之一。在这里，我们报告说，Fowler-Nordheim（FN）量子隧道设备可以实现突触存储器巩固，类似于通过算法合并模型（例如级联和弹性重量合并（EWC）模型）所能实现的。拟议的FN-Synapse不仅存储突触重量，而且还存储了Synapse在设备本身上的历史用法统计量。我们还表明，就突触寿命而言，FN合并的操作几乎是最佳的，并且我们证明了一个包含FN合成的网络在一个小基准测试持续学习任务上超过了可比的EWC网络。通过每次突触更新的Femtojoules的能量足迹，我们相信所提出的FN-Synapse为实施突触记忆巩固和持续学习提供了一种超能效率的方法。

构建用于仇恨语音检测的基准数据集具有各种挑战。首先，因为仇恨的言论相对少见，随机抽样对诠释的推文是非常效率的发现仇恨。为了解决此问题，先前的数据集通常仅包含匹配已知的“讨厌字”的推文。然而，将数据限制为预定义的词汇表可能排除我们寻求模型的现实世界现象的部分。第二个挑战是仇恨言论的定义往往是高度不同和主观的。具有多种讨论仇恨言论的注释者可能不仅可能不同意彼此不同意，而且还努力符合指定的标签指南。我们的重点识别是仇恨语音的罕见和主体性类似于信息检索（IR）中的相关性。此连接表明，可以有效地应用创建IR测试集合的良好方法，以创建更好的基准数据集以进行仇恨语音。为了智能和有效地选择要注释的推文，我们应用{\ em汇集}和{em主动学习}的标准IR技术。为了提高注释的一致性和价值，我们应用{\ EM任务分解}和{\ EM注释器理由}技术。我们在Twitter上共享一个用于仇恨语音检测的新基准数据集，其提供比以前的数据集更广泛的仇恨覆盖。在这些更广泛形式的仇恨中测试时，我们还表现出现有检测模型的准确性的戏剧性降低。注册器理由我们不仅可以证明标签决策证明，而且还可以在建模中实现未来的双重监督和/或解释生成的工作机会。我们的方法的进一步细节可以在补充材料中找到。

Pneumonia, a respiratory infection brought on by bacteria or viruses, affects a large number of people, especially in developing and impoverished countries where high levels of pollution, unclean living conditions, and overcrowding are frequently observed, along with insufficient medical infrastructure. Pleural effusion, a condition in which fluids fill the lung and complicate breathing, is brought on by pneumonia. Early detection of pneumonia is essential for ensuring curative care and boosting survival rates. The approach most usually used to diagnose pneumonia is chest X-ray imaging. The purpose of this work is to develop a method for the automatic diagnosis of bacterial and viral pneumonia in digital x-ray pictures. This article first presents the authors' technique, and then gives a comprehensive report on recent developments in the field of reliable diagnosis of pneumonia. In this study, here tuned a state-of-the-art deep convolutional neural network to classify plant diseases based on images and tested its performance. Deep learning architecture is compared empirically. VGG19, ResNet with 152v2, Resnext101, Seresnet152, Mobilenettv2, and DenseNet with 201 layers are among the architectures tested. Experiment data consists of two groups, sick and healthy X-ray pictures. To take appropriate action against plant diseases as soon as possible, rapid disease identification models are preferred. DenseNet201 has shown no overfitting or performance degradation in our experiments, and its accuracy tends to increase as the number of epochs increases. Further, DenseNet201 achieves state-of-the-art performance with a significantly a smaller number of parameters and within a reasonable computing time. This architecture outperforms the competition in terms of testing accuracy, scoring 95%. Each architecture was trained using Keras, using Theano as the backend.

Training of a Machine Learning model requires sufficient data. The sufficiency of the data is not always about the quantity, but about the relevancy and reduced redundancy. Data-generating processes create massive amounts of data. When used raw, such big data is causing much computational resource utilization. Instead of using the raw data, a proper Condensed Representation can be used instead. Combining K-means, a well-known clustering method, with some correction and refinement facilities a novel Condensed Representation method for Machine Learning applications is introduced. To present the novel method meaningfully and visually, synthetically generated data is employed. It has been shown that by using the condensed representation, instead of the raw data, acceptably accurate model training is possible.

We present temporally layered architecture (TLA), a biologically inspired system for temporally adaptive distributed control. TLA layers a fast and a slow controller together to achieve temporal abstraction that allows each layer to focus on a different time-scale. Our design is biologically inspired and draws on the architecture of the human brain which executes actions at different timescales depending on the environment's demands. Such distributed control design is widespread across biological systems because it increases survivability and accuracy in certain and uncertain environments. We demonstrate that TLA can provide many advantages over existing approaches, including persistent exploration, adaptive control, explainable temporal behavior, compute efficiency and distributed control. We present two different algorithms for training TLA: (a) Closed-loop control, where the fast controller is trained over a pre-trained slow controller, allowing better exploration for the fast controller and closed-loop control where the fast controller decides whether to "act-or-not" at each timestep; and (b) Partially open loop control, where the slow controller is trained over a pre-trained fast controller, allowing for open loop-control where the slow controller picks a temporally extended action or defers the next n-actions to the fast controller. We evaluated our method on a suite of continuous control tasks and demonstrate the advantages of TLA over several strong baselines.

Pruning refers to the elimination of trivial weights from neural networks. The sub-networks within an overparameterized model produced after pruning are often called Lottery tickets. This research aims to generate winning lottery tickets from a set of lottery tickets that can achieve similar accuracy to the original unpruned network. We introduce a novel winning ticket called Cyclic Overlapping Lottery Ticket (COLT) by data splitting and cyclic retraining of the pruned network from scratch. We apply a cyclic pruning algorithm that keeps only the overlapping weights of different pruned models trained on different data segments. Our results demonstrate that COLT can achieve similar accuracies (obtained by the unpruned model) while maintaining high sparsities. We show that the accuracy of COLT is on par with the winning tickets of Lottery Ticket Hypothesis (LTH) and, at times, is better. Moreover, COLTs can be generated using fewer iterations than tickets generated by the popular Iterative Magnitude Pruning (IMP) method. In addition, we also notice COLTs generated on large datasets can be transferred to small ones without compromising performance, demonstrating its generalizing capability. We conduct all our experiments on Cifar-10, Cifar-100 & TinyImageNet datasets and report superior performance than the state-of-the-art methods.

Search and Rescue (SAR) missions in remote environments often employ autonomous multi-robot systems that learn, plan, and execute a combination of local single-robot control actions, group primitives, and global mission-oriented coordination and collaboration. Often, SAR coordination strategies are manually designed by human experts who can remotely control the multi-robot system and enable semi-autonomous operations. However, in remote environments where connectivity is limited and human intervention is often not possible, decentralized collaboration strategies are needed for fully-autonomous operations. Nevertheless, decentralized coordination may be ineffective in adversarial environments due to sensor noise, actuation faults, or manipulation of inter-agent communication data. In this paper, we propose an algorithmic approach based on adversarial multi-agent reinforcement learning (MARL) that allows robots to efficiently coordinate their strategies in the presence of adversarial inter-agent communications. In our setup, the objective of the multi-robot team is to discover targets strategically in an obstacle-strewn geographical area by minimizing the average time needed to find the targets. It is assumed that the robots have no prior knowledge of the target locations, and they can interact with only a subset of neighboring robots at any time. Based on the centralized training with decentralized execution (CTDE) paradigm in MARL, we utilize a hierarchical meta-learning framework to learn dynamic team-coordination modalities and discover emergent team behavior under complex cooperative-competitive scenarios. The effectiveness of our approach is demonstrated on a collection of prototype grid-world environments with different specifications of benign and adversarial agents, target locations, and agent rewards.

The task of locating and classifying different types of vehicles has become a vital element in numerous applications of automation and intelligent systems ranging from traffic surveillance to vehicle identification and many more. In recent times, Deep Learning models have been dominating the field of vehicle detection. Yet, Bangladeshi vehicle detection has remained a relatively unexplored area. One of the main goals of vehicle detection is its real-time application, where `You Only Look Once' (YOLO) models have proven to be the most effective architecture. In this work, intending to find the best-suited YOLO architecture for fast and accurate vehicle detection from traffic images in Bangladesh, we have conducted a performance analysis of different variants of the YOLO-based architectures such as YOLOV3, YOLOV5s, and YOLOV5x. The models were trained on a dataset containing 7390 images belonging to 21 types of vehicles comprising samples from the DhakaAI dataset, the Poribohon-BD dataset, and our self-collected images. After thorough quantitative and qualitative analysis, we found the YOLOV5x variant to be the best-suited model, performing better than YOLOv3 and YOLOv5s models respectively by 7 & 4 percent in mAP, and 12 & 8.5 percent in terms of Accuracy.

Deep learning (DL) models of code have recently reported great progress for vulnerability detection. In some cases, DL-based models have outperformed static analysis tools. Although many great models have been proposed, we do not yet have a good understanding of these models. This limits the further advancement of model robustness, debugging, and deployment for the vulnerability detection. In this paper, we surveyed and reproduced 9 state-of-the-art (SOTA) deep learning models on 2 widely used vulnerability detection datasets: Devign and MSR. We investigated 6 research questions in three areas, namely model capabilities, training data, and model interpretation. We experimentally demonstrated the variability between different runs of a model and the low agreement among different models' outputs. We investigated models trained for specific types of vulnerabilities compared to a model that is trained on all the vulnerabilities at once. We explored the types of programs DL may consider "hard" to handle. We investigated the relations of training data sizes and training data composition with model performance. Finally, we studied model interpretations and analyzed important features that the models used to make predictions. We believe that our findings can help better understand model results, provide guidance on preparing training data, and improve the robustness of the models. All of our datasets, code, and results are available at https://figshare.com/s/284abfba67dba448fdc2.

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of exploration, resulting from the variance of the representing distribution. Entropy can play an essential role in policy optimization by selecting the stochastic policy, which eventually helps better explore the environment in reinforcement learning (RL). However, the stochasticity often reduces as the training progresses; thus, the policy becomes less exploratory. Additionally, certain parametric distributions might only work for some environments and require extensive hyperparameter tuning. This paper aims to mitigate these issues. In particular, we propose an algorithm called Robust Policy Optimization (RPO), which leverages a perturbed distribution. We hypothesize that our method encourages high-entropy actions and provides a way to represent the action space better. We further provide empirical evidence to verify our hypothesis. We evaluated our methods on various continuous control tasks from DeepMind Control, OpenAI Gym, Pybullet, and IsaacGym. We observed that in many settings, RPO increases the policy entropy early in training and then maintains a certain level of entropy throughout the training period. Eventually, our agent RPO shows consistently improved performance compared to PPO and other techniques: entropy regularization, different distributions, and data augmentation. Furthermore, in several settings, our method stays robust in performance, while other baseline mechanisms fail to improve and even worsen the performance.