With the impressive progress of deep learning, applications relying on machine learning are increasingly being integrated into daily life. However, most deep learning models have an opaque, oracle-like nature making it difficult to interpret and understand their decisions. This problem led to the development of the field known as eXplainable Artificial Intelligence (XAI). One method in this field known as Projective Simulation (PS) models a chain-of-thought as a random walk of a particle on a graph with vertices that have concepts attached to them. While this description has various benefits, including the possibility of quantization, it cannot be naturally used to model thoughts that combine several concepts simultaneously. To overcome this limitation, we introduce Multi-Excitation Projective Simulation (mePS), a generalization that considers a chain-of-thought to be a random walk of several particles on a hypergraph. A definition for a dynamic hypergraph is put forward to describe the agent's training history along with applications to AI and hypergraph visualization. An inductive bias inspired by the remarkably successful few-body interaction models used in quantum many-body physics is formalized for our classical mePS framework and employed to tackle the exponential complexity associated with naive implementations of hypergraphs. We prove that our inductive bias reduces the complexity from exponential to polynomial, with the exponent representing the cutoff on how many particles can interact. We numerically apply our method to two toy environments and a more complex scenario modelling the diagnosis of a broken computer. These environments demonstrate the resource savings provided by an appropriate choice of inductive bias, as well as showcasing aspects of interpretability. A quantum model for mePS is also briefly outlined and some future directions for it are discussed.
With the impressive progress of deep learning, applications relying on machine learning are increasingly being integrated into daily life. However, most deep learning models have an opaque, oracle-like nature making it difficult to interpret and understand their decisions. This problem led to the development of the field known as eXplainable Artificial Intelligence (XAI). One method in this field known as Projective Simulation (PS) models a chain-of-thought as a random walk of a particle on a graph with vertices that have concepts attached to them. While this description has various benefits, including the possibility of quantization, it cannot be naturally used to model thoughts that combine several concepts simultaneously. To overcome this limitation, we introduce Multi-Excitation Projective Simulation (mePS), a generalization that considers a chain-of-thought to be a random walk of several particles on a hypergraph. A definition for a dynamic hypergraph is put forward to describe the agent's training history along with applications to AI and hypergraph visualization. An inductive bias inspired by the remarkably successful few-body interaction models used in quantum many-body physics is formalized for our classical mePS framework and employed to tackle the exponential complexity associated with naive implementations of hypergraphs. We prove that our inductive bias reduces the complexity from exponential to polynomial, with the exponent representing the cutoff on how many particles can interact. We numerically apply our method to two toy environments and a more complex scenario modelling the diagnosis of a broken computer. These environments demonstrate the resource savings provided by an appropriate choice of inductive bias, as well as showcasing aspects of interpretability. A quantum model for mePS is also briefly outlined and some future directions for it are discussed.
With the impressive progress of deep learning, applications relying on machine learning are increasingly being integrated into daily life. However, most deep learning models have an opaque, oracle-like nature that makes it difficult to interpret and understand their decisions. This problem led to the development of the field known as eXplainable Artificial Intelligence (XAI). One method in this field known as Projective Simulation (PS) models a chain-of-thought as a random walk of a particle on a graph with vertices that have concepts attached to them. While this description has various benefits, including the possibility of quantization, it cannot be naturally used to model thoughts that combine several concepts simultaneously. To overcome this limitation, we introduce Multi-Excitation Projective Simulation (MEPS), a generalization that considers a chain-of-thought to be a random walk of several particles on a hypergraph. A definition for a dynamic hypergraph is put forward to describe the agent’s training history along with applications to AI and hypergraph visualization. An inductive bias inspired by the remarkably successful few-body interaction models used in quantum many-body physics is formalized for our classical MEPS framework and employed to tackle the exponential complexity associated with naive implementations of hypergraphs. We prove that our inductive bias reduces the complexity from exponential to polynomial, with the exponent representing the cutoff on the number of particles that can interact. We numerically apply our method to two toy model environments and a more complex scenario that models the diagnosis of a broken computer. These environments demonstrate the resource savings provided by an appropriate choice of the inductive bias, as well as showcasing aspects of interpretability. A quantum model for MEPS is also briefly outlined and some future directions for it are discussed.
Abstract Variational quantum algorithms represent a promising approach to quantum machine learning where classical neural networks are replaced by parametrized quantum circuits. However, both approaches suffer from a clear limitation, that is a lack of interpretability. Here, we present a variational method to quantize projective simulation (PS), a reinforcement learning model aimed at interpretable artificial intelligence. Decision making in PS is modeled as a random walk on a graph describing the agent’s memory. To implement the quantized model, we consider quantum walks of single photons in a lattice of tunable Mach–Zehnder interferometers trained via variational algorithms. Using an example from transfer learning, we show that the quantized PS model can exploit quantum interference to acquire capabilities beyond those of its classical counterpart. Finally, we discuss the role of quantum interference for training and tracing the decision making process, paving the way for realizations of interpretable quantum learning agents.
In the past decade, deep learning methods have seen tremendous success in various supervised and unsupervised learning tasks such as classification and generative modeling. More recently, deep neural networks have emerged in the domain of reinforcement learning as a tool to solve decision-making problems of unprecedented complexity, e.g., navigation problems or game-playing AI. Despite the successful combinations of ideas from quantum computing with machine learning methods, there have been relatively few attempts to design quantum algorithms that would enhance deep reinforcement learning. This is partly due to the fact that quantum enhancements of deep neural networks, in general, have not been as extensively investigated as other quantum machine learning methods. In contrast, projective simulation is a reinforcement learning model inspired by the stochastic evolution of physical systems that enables a quantum speed-up in decision making. In this paper, we develop a unifying framework that connects deep learning and projective simulation, opening the route to quantum improvements in deep reinforcement learning. Our approach is based on so-called generative energy-based models to design reinforcement learning methods with a computational advantage in solving complex and large-scale decision-making problems.
The rapid advancement of Artificial Intelligence (AI) has heightened concerns about the opacity of decision-making processes in complex models, particularly deep neural networks. This research explores a novel paradigm that integrates quantum computing principles into Explainable AI (XAI) to enhance interpretability without compromising predictive accuracy. The study introduces a Quantum-inspired Interpretable Model (QIIM) framework that leverages Hilbert space embeddings, unitary transformations, and operator-based learning to represent knowledge in a mathematically transparent form. The proposed model computes interpretability through the expectation values of observable operators, enabling the decomposition of decisions into quantifiable, human-understandable components. To capture hierarchical relationships, a Tensor Network Interpretable Model (TNIM) is further developed, offering scalable insights into complex dependencies among features. Experimental evaluations—performed on benchmark datasets for decision-making tasks—demonstrate that the quantum-inspired models achieve competitive accuracy while significantly improving local and global interpretability metrics compared to classical XAI techniques. The findings underscore the potential of quantum formalism as a new foundation for transparent AI systems, bridging the gap between computational efficiency and explainability. This study contributes to both theoretical understanding and practical advancement in interpretable machine learning, paving the way for ethically aligned, transparent, and human-trustworthy AI-driven decision support systems.
Projective Simulation was introduced as a novel approach to Artificial Intelligence. It involves a deliberation procedure that consists of a random walk on a graph of clips and allows for the learning agent to project itself into the future before committing to an action. Here we study and analyze a quantum mechanical version in which the random walk is performed by two kinds of Hamiltonians. The first kind is implemented by naively embedding the classical model in a quantum model by turning the clips into qubits. The other allows for storing clips in superpositions of qubits allowing for a potentially purely quantum mechanical learning procedure in which the perception of the environment is purely quantum mechanical but the action is classical. We lastly introduce the concept of interacting projective agents for both the classical and quantum mechanical case.
Abstract Projective Simulation (PS) is a model for agency that incorporates aspects of reinforcement learning, an indeterministic basic dynamics inspired by physical hopping processes as studied in quantum optics, and an overall orientation towards agency as a continuous process of interaction with the environment as described by phenomenology. We explain the formal structure of PS in detail and compare it to the more standard paradigm of reinforcement learning. PS stands out mostly due to its specific memory structure (Episodic and Compositional Memory, ECM) and its openness, which makes it apt as an agency model rather than just a learning model: PS does not start from a fixed environment model to be “solved”. The focus is, rather, on the internal dynamics of deliberation, which is resolved as a stochastic process within the ECM, as well as on learning and adaptation over a long time, allowing for significant and even disruptive changes in the environment to be incorporated. After discussing the model, we showcase several applications of PS, prominently in basic research in quantum mechanics and especially in quantum information. This strengthens our claim about the intimate connection between agency and quantum physics that we already defended in Chaps. 3 and 4 . We also consider quantum versions of PS, which promise to show quantum advantages in machine learning while retaining a maximum of transparency. These applications motivate a separate discussion of transparency and traceability in the context of explainable (quantum) AI.