相关论文: Episodic source memory over distribution by quantu…

Emerging personal AI agents are moving toward persistent, multi-source memory. This creates an evaluation problem: systems must decide how to use conflicting or incomplete evidence; they cannot just retrieve facts from one clean history.…

We consider episodic reinforcement learning in reward-mixing Markov decision processes (RMMDPs): at the beginning of every episode nature randomly picks a latent reward model among $M$ candidates and an agent interacts with the MDP…

We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts:…

Robots must verbalize their past experiences when users ask "Where did you put my keys?" or "Why did the task fail?" Yet maintaining life-long episodic memory (EM) from continuous multimodal perception quickly exceeds storage limits and…

Unravelling the source of quantum computing power has been a major goal in the field of quantum information science. In recent years, the quantum resource theory (QRT) has been established to characterize various quantum resources, yet…

We study the functioning of associative memory on three-level quantum elements, qutrites represented by spins with S = 1. The recording of patterns into the superposition of quantum states and their recall are carried out by adiabatic…

Given the Hamiltonian, the evaluation of unitary operators has been at the heart of many quantum algorithms. Motivated by existing deterministic and random methods, we present a hybrid approach, where Hamiltonians with large amplitude are…

Memory is the fundamental form of temporal complexity: when present but uncontrollable, it manifests as non-Markovian noise; conversely, if controllable, memory can be a powerful resource for information processing. Memory effects arise…

Memory is critical for dialogue agents to maintain coherence and enable continuous adaptation in long-term interactions. While existing memory mechanisms offer basic storage and retrieval capabilities, they are hindered by two primary…

This paper proposes a general quantum algorithm that can be applied to any classical computer program. Each computational step is written using reversible operators, but the operators remain classical in that the qubits take on values of…

This work introduces the Query/Hit (Q/H) learning model. The setup consists of two agents. One agent, Alice, has access to a streaming source, while the other, Bob, does not have direct access to the source. Communication occurs through…

We review our models of quantum associative memories that represent the "quantization" of fully coupled neural networks like the Hopfield model. The idea is to replace the classical irreversible attractor dynamics driven by an Ising model…

Working memory often appears to exceed its basic span by organizing items into compact representations called chunks. Chunking can be learned over time for familiar inputs; however, it can also arise spontaneously for novel stimuli. Such…

We introduce an Attention Overload Model that captures the idea that alternatives compete for the decision maker's attention, and hence the attention that each alternative receives decreases as the choice problem becomes larger. Using this…

In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But…

QA models based on pretrained language mod-els have achieved remarkable performance on various benchmark datasets.However, QA models do not generalize well to unseen data that falls outside the training distribution, due to distributional…

An empirical model is a generalization of a probability space. It consists of a simplicial complex of subsets of a class X of random variables such that each simplex has an associated probability distribution. The ensuing marginalizations…

In this article we consider an experimental study showing the influence of emotion regulation strategies on human memory performance: part of such experimental results are difficult to explain within a classic cognitive allocation model. We…

Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item representations aligned with Knowledge Components, they overlook the procedural dynamics…

We introduce the Mutual Information Machine (MIM), a probabilistic auto-encoder for learning joint distributions over observations and latent variables. MIM reflects three design principles: 1) low divergence, to encourage the encoder and…