This paper investigates the impact of changes in agents' beliefs coupled with dynamics in agents' meta-roles on the evolution of institutions. The study embeds agents' meta-roles in the BDI architecture. In this context, the study scrutinises the impact of cognitive dissonance in agents due to unfairness of institutions. To showcase our model, two historical long-distance trading societies, namely Armenian merchants of New-Julfa and the English East India Company are simulated. Results show how change in roles of agents coupled with specific institutional characteristics leads to changes of the rules in the system.

In the past decades, the rapid growth of computer and database technologies has led to the rapid growth of large-scale datasets. On the other hand, data mining applications with high dimensional datasets that require high speed and accuracy are rapidly increasing. An important issue with these applications is the curse of dimensionality, where the number of features is much higher than the number of patterns. One of the dimensionality reduction approaches is feature selection that can increase the accuracy of the data mining task and reduce its computational complexity. The feature selection method aims at selecting a subset of features with the lowest inner similarity and highest relevancy to the target class. It reduces the dimensionality of the data by eliminating irrelevant, redundant, or noisy data. In this paper, a comparative analysis of different feature selection methods is presented, and a general categorization of these methods is performed. Moreover, in this paper, state-of-the-art swarm intelligence are studied, and the recent feature selection methods based on these algorithms are reviewed. Furthermore, the strengths and weaknesses of the different studied swarm intelligence-based feature selection methods are evaluated.

This paper studies the relationship between generalization and privacy preservation in iterative learning algorithms by two sequential steps. We first establish an alignment between generalization and privacy preservation for any learning algorithm. We prove that $(\varepsilon, \delta)$-differential privacy implies an on-average generalization bound for multi-database learning algorithms which further leads to a high-probability bound for any learning algorithm. This high-probability bound also implies a PAC-learnable guarantee for differentially private learning algorithms. We then investigate how the iterative nature shared by most learning algorithms influence privacy preservation and further generalization. Three composition theorems are proposed to approximate the differential privacy of any iterative algorithm through the differential privacy of its every iteration. By integrating the above two steps, we eventually deliver generalization bounds for iterative learning algorithms, which suggest one can simultaneously enhance privacy preservation and generalization. Our results are strictly tighter than the existing works. Particularly, our generalization bounds do not rely on the model size which is prohibitively large in deep learning. This sheds light to understanding the generalizability of deep learning. These results apply to a wide spectrum of learning algorithms. In this paper, we apply them to stochastic gradient Langevin dynamics and agnostic federated learning as examples.

The move set off a wave of criticism from many Democratic and some Republican lawmakers, who said the decision undermined the pact. By ignoring a part of the agreement it finds inconvenient, they say, the Trump administration is encouraging other nations to do the same. And the sale of advanced armed drones could lead to the proliferation of the technology across the globe. The lawmakers are especially concerned about sales to Saudi Arabia and the United Arab Emirates, which have used American-made weapons to carry out a devastating war in Yemen that has left thousands of civilians, many of them children, dead. "If we allow Trump to start selling drones, we set a dangerous precedent that allows and encourages other countries to sell missile technology and advanced drones to our adversaries," Senator Christopher S. Murphy, Democrat of Connecticut and a sponsor of the bill, said in a statement on Wednesday.

Republican and Democratic senators introduced legislation on Thursday that would block international sales of United States-made drones to countries that are not close US allies, mentioning Saudi Arabia in particular. Reuters broke the news in June that President Donald Trump's administration planned to reinterpret the Missile Technology Control Regime, a Cold War arms agreement between 35 nations, with the goal of allowing US defence contractors to sell more drones to an array of nations. Republican Senators Mike Lee and Rand Paul, Democratic Senators Chris Murphy and Chris Coons, and Senator Bernie Sanders, an independent who caucuses with Democrats, introduced the measure. It would amend the Arms Export Control Act to prohibit the export, transfer or trade of many advanced drones except to countries that are NATO members and to Australia, New Zealand, South Korea, Japan and Israel, they said in a news release. US lawmakers have tried before to rein in Trump administration plans for arms sales, particularly to Saudi Arabia and the United Arab Emirates for use in the war in Yemen.

The accuracy and flexibility of facial recognition technology has seen it securing everything from smartphones to Australia's airports, but a team of security researchers is warning of potential manipulation after finding a way to trick the systems using deepfake images. Researchers within the McAfee Advanced Threat Research (ATR) team have been exploring ways that'model hacking' – also known as adversarial machine learning – can be used to trick artificial intelligence (AI) computer-vision algorithms into misidentifying the content of the images they see. This approach has previously been used to show how autonomous-car safety systems, which can read speed-limit signs and adjust the car's speed accordingly, could be tricked by modifying street signs with stickers that were misread by the systems. Subtle modifications to the signs would be picked up by the computer-vision algorithms but might be indiscernible to the human eye – an approach that the McAfee team has now successfully turned towards the challenge of identifying people from photos, as in the screening of passports. Starting with photos of two people – called A and B – ATR researchers used what they described as a "deep learning-based morphing approach" to generate large numbers of composite images that combined features from both.

Although for many organizations artificial intelligence may be a work in progress, its rapid spread across the enterprise has led Gartner to predict that by 2024, 75% of organizations will shift from piloting to operationalizing artificial intelligence (AI). This in turn will drive an increase in streaming data and analytics infrastructures by up to 500%. It is likely that the current health crisis has sped up the rate of deployment. During the pandemic and with millions working from home, AI techniques such as machine learning (ML), optimization and natural language processing (NLP) have been able to provide insights and predictions about the spread of the virus and the effectiveness and impact of countermeasures. It has also enabled many organizations to continue doing business where they might otherwise have had to slow down or even shut down.

Deep Q-Network (DQN) based multi-agent systems (MAS) for reinforcement learning (RL) use various schemes where in the agents have to learn and communicate. The learning is however specific to each agent and communication may be satisfactorily designed for the agents. As more complex Deep Q-Networks come to the fore, the overall complexity of the multi-agent system increases leading to issues like difficulty in training, need for higher resources and more training time, difficulty in fine-tuning, etc. To address these issues we propose a simple but efficient DQN based MAS for RL which uses shared state and rewards, but agent-specific actions, for updation of the experience replay pool of the DQNs, where each agent is a DQN. The benefits of the approach are overall simplicity, faster convergence and better performance as compared to conventional DQN based approaches. It should be noted that the method can be extended to any DQN. As such we use simple DQN and DDQN (Double Q-learning) respectively on three separate tasks i.e. Cartpole-v1 (OpenAI Gym environment), LunarLander-v2 (OpenAI Gym environment) and Maze Traversal (customized environment). The proposed approach outperforms the baseline on these tasks by decent margins respectively.

Benefiting from advances in machine vision and natural language processing techniques, current image captioning systems are able to generate detailed visual descriptions. For the most part, these descriptions represent an objective characterisation of the image, although some models do incorporate subjective aspects related to the observer's view of the image, such as sentiment; current models, however, usually do not consider the emotional content of images during the caption generation process. This paper addresses this issue by proposing novel image captioning models which use facial expression features to generate image captions. The models generate image captions using long short-term memory networks applying facial features in addition to other visual features at different time steps. We compare a comprehensive collection of image captioning models with and without facial features using all standard evaluation metrics. The evaluation metrics indicate that applying facial features with an attention mechanism achieves the best performance, showing more expressive and more correlated image captions, on an image caption dataset extracted from the standard Flickr 30K dataset, consisting of around 11K images containing faces. An analysis of the generated captions finds that, perhaps unexpectedly, the improvement in caption quality appears to come not from the addition of adjectives linked to emotional aspects of the images, but from more variety in the actions described in the captions.

Increasing demand for on-device Automatic Speech Recognition (ASR) systems has resulted in renewed interests in developing automatic model compression techniques. Past research have shown that AutoML-based Low Rank Factorization (LRF) technique, when applied to an end-to-end Encoder-Attention-Decoder style ASR model, can achieve a speedup of up to 3.7x, outperforming laborious manual rank-selection approaches. However, we show that current AutoML-based search techniques only work up to a certain compression level, beyond which they fail to produce compressed models with acceptable word error rates (WER). In this work, we propose an iterative AutoML-based LRF approach that achieves over 5x compression without degrading the WER, thereby advancing the state-of-the-art in ASR compression.