This thesis investigates the contribution of quantum computers to machine learning, a field called Quantum Machine Learning. Quantum Machine Learning promises innovative perspectives and methods... Show moreThis thesis investigates the contribution of quantum computers to machine learning, a field called Quantum Machine Learning. Quantum Machine Learning promises innovative perspectives and methods for solving complex problems in machine learning, leveraging the unique capabilities of quantum computers. These computers differ fundamentally from classical computers by exploiting certain quantum mechanical phenomena. The thesis explores various proposals within quantum machine learning, such as the application of quantum algorithms in topological data analysis. With respect to topological data analysis, results demonstrate that quantum algorithms solve problems considered inefficient in classical settings. The thesis also explores structural risk minimization in quantum machine learning models, identifying crucial design choices for new quantum machine learning models. Additionally, it introduces quantum models in reinforcement learning, which deliver comparable performance to traditional models and are superior in certain scenarios. The final part identifies learning tasks in computational learning theory where quantum learning algorithms have exponential advantages. In summary, this thesis contributes to understanding how quantum computers can address complex machine learning problems, from topological data analysis to reinforcement learning and computational learning tasks. Show less
Over several decades, a variety of computational methods for drug discovery have been proposed and applied in practice. With the accumulation of data and the development of machine learning methods... Show moreOver several decades, a variety of computational methods for drug discovery have been proposed and applied in practice. With the accumulation of data and the development of machine learning methods, computational drug design methods have gradually shifted to a new paradigm, i.e. deep learning methods have attracted particular interest in drug design. In this study, a new deep learning-based method (DrugEx) was proposed to design de novo drug-like molecules. It was proven that candidate molecules designed by DrugEx had a larger chemical diversity, and better covered the chemical space of known ligands. In order to address the issue of polypharmacology, the DrugEx algorithm was updated with multi-objective optimization towards multiple targets. The results of its application demonstrated the generation of compounds with a diverse predicted selectivity profile toward multiple targets, offering the potential of high efficacy and lower toxicity. In order to improve its generality, DrugEx was further updated to have the capability of designing molecules based on given scaffolds. We extended the architecture of Transformer to deal with each molecule as a graph. As a proof, its effectiveness in that 100% valid molecules are generated and most of them had predicted high affinity towards A2AAR with given scaffolds. Moreover, GenUI was developed as a visualizion software platform that makes it possible to integrate molecular generators within a feature-rich graphical user interface to facilitate collaboration in the disparate communities interested in computer-aided drug discovery.These studies highlight the overwhelming power of AI methods in drug discovery. Show less
After the recent groundbreaking results of AlphaGo and AlphaZero, we have seen strong interests in deep reinforcement learning and artificial general intelligence (AGI) in game playing. However,... Show moreAfter the recent groundbreaking results of AlphaGo and AlphaZero, we have seen strong interests in deep reinforcement learning and artificial general intelligence (AGI) in game playing. However, deep learning is resource-intensive and the theory is not yet well developed. For small games, simple classical table-based Q-learning might still be the algorithm of choice. General Game Playing (GGP) provides a good testbed for reinforcement learning to research AGI. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee & Stone, IJCAI 2007) in GGP. In this paper we implement Q-learning in GGP for three small-board games (Tic-Tac-Toe, Connect Four, Hex), to allow comparison to Banerjee et al. We find that Q-learning converges to a high win rate in GGP. For the ϵ" role="presentation" style="display: inline-table; line-height: normal; letter-spacing: normal; word-spacing: normal; overflow-wrap: normal; white-space: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0px; min-height: 0px; border-width: 0px; border-style: initial; position: relative;">ϵ-greedy strategy, we propose a first enhancement, the dynamic ϵ" role="presentation" style="display: inline-table; line-height: normal; letter-spacing: normal; word-spacing: normal; overflow-wrap: normal; white-space: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0px; min-height: 0px; border-width: 0px; border-style: initial; position: relative;">ϵ algorithm. In addition, inspired by (Gelly & Silver, ICML 2007) we combine online search (Monte Carlo Search) to enhance offline learning, and propose QM-learning for GGP. Both enhancements improve the performance of classical Q-learning. In this work, GGP allows us to show, if augmented by appropriate enhancements, that classical table-based Q-learning can perform well in small games. Show less
In this thesis we have studied the influence of emotion on learning. We have used computational modelling techniques to do so, more specifically, the reinforcement learning paradigm. Emotion is... Show moreIn this thesis we have studied the influence of emotion on learning. We have used computational modelling techniques to do so, more specifically, the reinforcement learning paradigm. Emotion is modelled as artificial affect, a measure that denotes the positiveness versus negativeness of a situation to an artificial agent in a reinforcement learning setting. We have done a range of different experiments to study the effect of affect on learning, including the effect on learning if affect is used to control the exploration behaviour of the agent and the effect on learning when affect is communicated by a human (though real-time analysis of that human__s facial expressions) to a simulated robot. We conclude that affect is a useful concept to consider in adaptive agents that learn based on reinforcement learning and that in some cases affect can indeed help the learning process. Further, affective modelling in this way can help understand the psychological processes that underlie influences of affect on cognition. Finally, we have developed a formal notation for a specific type of emotion theory, i.e., cognitive appraisal theory. Show less
