Related papers: On Transformations of Load-Store Maurer Instructio…
Two of the many trends in neural network research of the past few years have been (i) the learning of dynamical systems, especially with recurrent neural networks such as long short-term memory networks (LSTMs) and (ii) the introduction of…
Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation. However, existing approaches face a dilemma: modular systems rely on explicit mapping but lack flexibility,…
Variations in the band structures of C60-polymers are studied, when pi-conjugation conditions are changed. We look at band structures in order to discuss a metal-insulator transition, using a semi-empirical model with the…
Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…
We studied topological and metric properties of the so-called interval translation maps (ITMs). For these maps, we introduced the maximal invariant measure and study its properties. Further, we study how the invariant measures depend on the…
The deployment of Large Language Models (LLMs) on consumer edge devices is throttled by the "Memory Wall" -- the prohibitive bandwidth and energy cost of fetching gigabytes of model weights from DRAM for every token generated. Current…
Numerical simulations of complex multiphysics systems, such as char combustion considered herein, yield numerous state variables that inherently exhibit physical constraints. This paper presents a new approach to augment Operator Inference…
Machine learning plays a critical role in extracting meaningful information out of the zetabytes of sensor data collected every day. For some applications, the goal is to analyze and understand the data to identify trends (e.g.,…
Machine learning models are often used to make predictions about admissions process outcomes, such as for colleges or jobs. However, such decision processes differ substantially from the conventional machine learning paradigm. Because…
We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions. We show that currently…
In principle, machine learning (ML) can be used to obtain any electronic property of a many-body system from its electron density within density functional theory. However, some physical quantities are highly sensitive to small variations…
Recent advancements in machine learning and reinforcement learning have brought increased attention to their applicability in a range of decision-making tasks in the operations of power systems, such as short-term emergency control,…
Typical constraints on embedded systems include code size limits, upper bounds on energy consumption and hard or soft deadlines. To meet these requirements, it may be necessary to improve the software by applying various kinds of…
Learning and Artificial Intelligence (ML/AI) techniques have become increasingly prevalent in high performance computing (HPC). However, these methods depend on vast volumes of floating point data for training and validation which need…
Disk access latency and transfer times are often considered to have a major and detrimental impact on the running time of software. Developers are often advised to favour in-memory operations and minimise disk access. Furthermore, diskless…
I present an informal discussion of various cases where two-dimensional surface metal-insulator structural and charge-density-wave instabilities driven by partly filled surface states have been advocated. These include reconstructions of…
The quality of the data in a dataset can have a substantial impact on the performance of a machine learning model that is trained and/or evaluated using the dataset. Effective dataset management, including tasks such as data cleanup,…
Recent studies demonstrated that there may appear different novel states in correlated systems close to localized-itinerant crossover. Especially favourable conditions for that are met in low-dimensional and in frustrated systems. In this…
Memory formation in matter is a theme of broad intellectual relevance; it sits at the interdisciplinary crossroads of physics, biology, chemistry, and computer science. Memory connotes the ability to encode, access, and erase signatures of…
Large language models exhibit sophisticated capabilities, yet understanding how they work internally remains a central challenge. A fundamental obstacle is that training selects for behavior, not circuitry, so many weight configurations can…