Related papers: On Transformations of Load-Store Maurer Instructio…

Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to…

Memristor, memory resistor, is an emerging technology for computational memory. Number of different memristor models are available based on the physical experiments. To use memristor as a computational memory element, one should know how…

Memory consistency models are notorious for being difficult to define precisely, to reason about, and to verify. More than a decade of effort has gone into nailing down the definitions of the ARM and IBM Power memory models, and yet there…

This paper presents an active inference method for Extended Finite State Machines, where inputs and outputs are parametrized, and transitions can be conditioned by guards involving input parameters and internal variables called registers.…

Ground state of the periodic Anderson model on a triangular lattice is systematically investigated by the mean-field approximation. We found that the model exhibits two different types of partially disordered states: one is at half filling…

We investigate learning collections of languages from texts by an inductive inference machine with access to the current datum and a bounded memory in form of states. Such a bounded memory states (BMS) learner is considered successful in…

Matrix functions play an increasingly important role in many areas of scientific computing and engineering disciplines. In such real-world applications, algorithms working in floating-point arithmetic are used for computing matrix functions…

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

In Partially Observable Markov Decision Processes, integrating an agent's history into memory poses a significant challenge for decision-making. Traditional imitation learning, relying on observation-action pairs for expert demonstrations,…

Memory is an important aspect of intelligence and plays a role in many deep reinforcement learning models. However, little progress has been made in understanding when specific memory systems help more than others and how well they…

Traditional memory writing operations proceed one bit at a time, where e.g. an individual magnetic domain is force-flipped by a localized external field. One way to increase material storage capacity would be to write several bits at a time…

Reinforcement Learning faces an important challenge in partial observable environments that has long-term dependencies. In order to learn in an ambiguous environment, an agent has to keep previous perceptions in a memory. Earlier memory…

We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performance in non-asymptotic data regimes to understand the role of…

In this paper we propose an approach for executing data transformations near- or in-storage on intelligent storage systems. The currently prevailing approach of extracting the data and then transforming it to a target format suffers…

Recent studies have demonstrated that the performance of transformers on the task of language modeling obeys a power-law relationship with model size over six orders of magnitude. While transformers exhibit impressive scaling, their…

The hardware/software boundary in modern heterogeneous multicore computers is increasingly complex, and diverse across different platforms. A single memory access by a core or DMA engine traverses multiple hardware translation and caching…

Neural operators, which emerge as implicit solution operators of hidden governing equations, have recently become popular tools for learning responses of complex real-world physical systems. Nevertheless, the majority of neural operator…

On-device machine learning is often constrained by limited storage, particularly in continuous data collection scenarios. This paper presents an empirical study on storage-aware learning, focusing on the trade-off between data quantity and…

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.

The memory model for RISC-V, a newly developed open source ISA, has not been finalized yet and thus, offers an opportunity to evaluate existing memory models. We believe RISC-V should not adopt the memory models of POWER or ARM, because…