Related papers: Memory Implementations - Current Alternatives
Humans exhibit complex motions that vary depending on the task that they are performing, the interactions they engage in, as well as subject-specific preferences. Therefore, forecasting future poses based on the history of the previous…
Forgetting refers to the loss or deterioration of previously acquired knowledge. While existing surveys on forgetting have primarily focused on continual learning, forgetting is a prevalent phenomenon observed in various other research…
Resource constraints can fundamentally change both learning and decision-making. We explore how memory constraints influence an agent's performance when navigating unknown environments using standard reinforcement learning algorithms.…
An important challenge for quantum theories of cognition and decision concerns the incorporation of memory for recently made judgments and their effects on later judgments. First, we review a general approach to measurement based on system…
An optical quantum memory can be broadly defined as a system capable of storing a useful quantum state through interaction with light at optical frequencies. During the last decade, intense research was devoted to their development, mostly…
Quantum memories are essential for quantum information processing and long-distance quantum communication. The field has recently seen a lot of progress, and the present focus issue offers a glimpse of these developments, showing both…
Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly,…
We consider an optimal control problem governed by an ODE with memory playing the role of a control. We show the existence of an optimal solution and derive some necessary optimality conditions. Some examples are then discussed.
Human memory has notable limitations (e.g., forgetting) which have necessitated a variety of memory aids (e.g., calendars). As we grow closer to mass adoption of everyday Extended Reality (XR), which is frequently leveraging perceptual…
Under a unified operational definition, we define LLM memory as a persistent state written during pretraining, finetuning, or inference that can later be addressed and that stably influences outputs. We propose a four-part taxonomy…
Quantum memory is important to quantum information processing in many ways: a synchronization device to match various processes within a quantum computer, an identity quantum gate that leaves any state unchanged, and a tool to convert…
Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…
Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent advancement of deep learning, the newly proposed Deep-RL…
AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act…
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…
Most languages use the relative order between words to encode meaning relations. Languages differ, however, in what orders they use and how these orders are mapped onto different meanings. We test the hypothesis that, despite these…
Existing attention mechanisms are trained to attend to individual items in a collection (the memory) with a predefined, fixed granularity, e.g., a word token or an image grid. We propose area attention: a way to attend to areas in the…
One explanation for how people can plan efficiently despite limited cognitive resources is that we possess a set of adaptive planning strategies and know when and how to use them. But how are these strategies acquired? While previous…
Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans. Applying knowledge gained from psychological studies, we designed a new model called…
Neurons are individually translated into simple gates to plan a brain based on human psychology and intelligence. State machines, assumed previously learned in subconscious associative memory are shown to enable equation solving and…