The Ultimatum Game (UG) is an abstraction of common human interactions. In the UG, two players split a resource by proposing and responding to deals. The Dictator Game is a simplified and constrained ...form of the UG where deals may not be rejected. In this paper, in an evolutionary spatial Dictator Game, a form of Edge Weight Learning that allows players to react to the strategies of their neighbours is proposed. Edge weights directly influence the likelihood of a recipient to decide to not interact with a dictator neighbour, punishing exploitative, greedier neighbours and rewarding cooperative, fairer neighbours. Through experimentation with environmental parameters such as the rate of edge weight modification and the rate of evolutionary phases, it is shown that this process inspired by edge weight learning may serve as a catalyst for the emergence of fairness in the evolutionary Dictator Game.
Federated Learning is an emerging approach to Machine Learning which allows for decentralised model training which safeguards privacy. Its potential applications, particularly in Medicine, Smart ...Manufacturing, Finance, and the Internet of Things, hold significant promise. However, it faces hurdles due to resource constraints and the diverse nature of data and devices at the client end. This paper highlights the critical challenge of client drift and its effects on Machine Learning model performance across various architectural configurations. Furthermore, our findings reveal that the use of pretrained models such as ResNet offers a compelling solution to mitigate the impact of client drift to some extent. Nonetheless, it is worth noting that leveraging pretrained models necessitates substantial client-side resources. In response to the dual challenges of client drift and resource constraints, we propose an innovative approach involving Knowledge Distillation, namely combining distillation loss and classification loss while using knowledge distillation at the client. Here, the teacher model is trained on a more compact dataset, while the student model undertakes training on a larger, more diverse dataset. This approach not only improves robustness but also enhances privacy. The outcomes of our experiments substantiate the efficacy of this technique, showcasing an approximate improvement of 50% in the accuracy and loss of the student model.
Near-infrared (NIR) spectroscopy is a simple and non-destructive technique that provides a wealth of information on the chemical composition and physical properties of a sample. NIR spectra are ...produced as a function of the energy transition between electromagnetic radiation in the near-infrared region (700 - 2500 nm) and matter. The spectra are complex and typically contain broad overlapping absorption bands that are difficult to interpret. Chemometrics is the field of study that encompasses various multivariate data analysis methods for qualitative and quantitative analysis of chemical data via methods such as spectroscopy. Due to the volatile nature of spectroscopic data, there is no one-size-fits-all approach to modelling such tasks. In this work, we perform a systematic review of various modelling approaches for the task of crop cultivar identification of Barley, Chickpea, and Sorghum grains. Our analysis includes two established discriminant analysis methods commonly applied in chemometrics, and three Machine Learning algorithms. Fur-thermore, we compare multiclass classification, as the task was originally represented, with a one-vs-rest classification approach. We demonstrate that one-vs-rest classification is a strong al-ternative modelling approach with the ability to improve the classification score and highlight the weaker target classes that affect performance in multiclass classification problems.
In current state-of-the-art commercial first person shooter games, computer controlled bots, also known as nonplayer characters, can often be easily distinguishable from those controlled by humans. ...Tell-tale signs such as failed navigation, "sixth sense" knowledge of human players' whereabouts and deterministic, scripted behaviors are some of the causes of this. We propose, however, that one of the biggest indicators of nonhumanlike behavior in these games can be found in the weapon shooting capability of the bot. Consistently perfect accuracy and "locking on" to opponents in their visual field from any distance are indicative capabilities of bots that are not found in human players. Traditionally, the bot is handicapped in some way with either a timed reaction delay or a random perturbation to its aim, which doesn't adapt or improve its technique over time. We hypothesize that enabling the bot to learn the skill of shooting through trial and error, in the same way a human player learns, will lead to greater variation in game-play and produce less predictable nonplayer characters. This paper describes a reinforcement learning shooting mechanism for adapting shooting over time based on a dynamic reward signal from the amount of damage caused to opponents.
This dissertation investigates the use of one-sided classification algorithms in the application of separating hazardous chlorinated solvents from other materials, based on their Raman spectra. The ...experimentation is carried out using a new one-sided classification toolkit that was designed and developed from the ground up. In the one-sided classification paradigm, the objective is to separate elements of the target class from all outliers. These one-sided classifiers are generally chosen, in practice, when there is a deficiency of some sort in the training examples. Sometimes outlier examples can be rare, expensive to label, or even entirely absent. However, this author would like to note that they can be equally applicable when outlier examples are plentiful but nonetheless not statistically representative of the complete outlier concept. It is this scenario that is explicitly dealt with in this research work. In these circumstances, one-sided classifiers have been found to be more robust that conventional multi-class classifiers. The term "unexpected" outliers is introduced to represent outlier examples, encountered in the test set, that have been taken from a different distribution to the training set examples. These are examples that are a result of an inadequate representation of all possible outliers in the training set. It can often be impossible to fully characterise outlier examples given the fact that they can represent the immeasurable quantity of "everything else" that is not a target. The findings from this research have shown the potential drawbacks of using conventional multi-class classification algorithms when the test data come from a completely different distribution to that of the training samples.
Serverless computing is the latest paradigm in cloud computing, offering a framework for the development of event driven, pay-as-you-go functions in a highly scalable environment. While these traits ...offer a powerful new development paradigm, they have also given rise to a new form of cyber-attack known as Denial of Wallet (forced financial exhaustion). In this work, we define and identify the threat of Denial of Wallet and its potential attack patterns. Also, we demonstrate how this new form of attack can potentially circumvent existing mitigation systems developed for a similar style of attack, Denial of Service. Our goal is twofold. Firstly, we will provide a concise and informative overview of this emerging attack paradigm. Secondly, we propose this paper as a starting point to enable researchers and service providers to create effective mitigation strategies. We include some simulated experiments to highlight the potential financial damage that such attacks can cause and the creation of an isolated test bed for continued safe research on these attacks.
Multi-class classification algorithms are very widely used, but we argue that they are not always ideal from a theoretical perspective, because they assume all classes are characterized by the data, ...whereas in many applications, training data for some classes may be entirely absent, rare, or statistically unrepresentative. We evaluate one-sided classifiers as an alternative, since they assume that only one class (the target) is well characterized. We consider a task of identifying whether a substance contains a chlorinated solvent, based on its chemical spectrum. For this application, it is not really feasible to collect a statistically representative set of outliers, since that group may contain anything apart from the target chlorinated solvents. Using a new one-sided classification toolkit, we compare a One-Sided k-NN algorithm with two well-known binary classification algorithms, and conclude that the one-sided classifier is more robust to unexpected outliers.
Serverless computing offers an event driven pay-as-you-go framework for application development. A key selling point is the concept of no back-end server management, allowing developers to focus on ...application functionality. This is achieved through severe abstraction of the underlying architecture the functions run on. We examine the underlying architecture and report on the performance of serverless functions and how they are effected by certain factors such as memory allocation and interference caused by load induced by other users on the platform. Specifically, we focus on the serverless offerings of the four largest platforms; AWS Lambda, Google Cloud Functions, Microsoft Azure Functions and IBM Cloud Functions}. In this paper, we observe and contrast between these platforms in their approach to the common issue of "cold starts", we devise a means to unveil the underlying architecture serverless functions execute on and we investigate the effects of interference from load on the platform over the time span of one month.
In this paper, we introduce a skill-balancing mechanism for adversarial non-player characters (NPCs), called Skilled Experience Catalogue (SEC). The objective of this mechanism is to approximately ...match the skill level of an NPC to an opponent in real-time. We test the technique in the context of a First- Person Shooter (FPS) game. Specifically, the technique adjusts a reinforcement learning NPC's proficiency with a weapon based on its current performance against an opponent. Firstly, a catalogue of experience, in the form of stored learning policies, is built up by playing a series of training games. Once the NPC has been sufficiently trained, the catalogue acts as a timeline of experience with incremental knowledge milestones in the form of stored learning policies. If the NPC is performing poorly, it can jump to a later stage in the learning timeline to be equipped with more informed decision-making. Likewise, if it is performing significantly better than the opponent, it will jump to an earlier stage. The NPC continues to learn in real-time using reinforcement learning but its policy is adjusted, as required, by loading the most suitable milestones for the current circumstances.