Related papers: Energy Constraints Improve Liquid State Machine Pe…
This paper examines the impact of static sparsity on the robustness of a trained network to weight perturbations, data corruption, and adversarial examples. We show that, up to a certain sparsity achieved by increasing network width and…
The increasing computational demands of transformer models in time series classification necessitate effective optimization strategies for energy-efficient deployment. Our study presents a systematic investigation of optimization…
In this paper, the impact of energy constraints on a two-hop network with a source, a relay and a destination under random medium access is studied. A collision channel with erasures is considered, and the source and the relay nodes have…
In the present work we investigate the effects of spatial constraints on the efficiency of task execution in systems underlain by geographical complex networks where the probability of connection decreases with the distance between the…
In recent times adaptive regulation of sampling rates has gained significant attention in research community and researchers has demonstrated it's effectiveness in embedded control applications from different perspectives. In low power…
Canonical ensemble molecular dynamics simulations of liquid methanol, modeled using a rigid-body, pair-additive potential, are used to compute static distributions and temporal correlations of tagged molecule potential energies as a means…
The advent of electronic computers has revolutionised the application of statistical mechanics to the liquid state. Computers have permitted, for example, the calculation of the phase diagram of water and ice and the folding of proteins.…
Power consumption in buildings show non-linear behaviors that linear models cannot capture whereas recurrent neural networks (RNNs) can. This ability makes RNNs attractive alternatives for the model-predictive control (MPC) of buildings.…
Load instructions often limit instruction-level parallelism (ILP) in modern processors due to data and resource dependences they cause. Prior techniques like Load Value Prediction (LVP) and Memory Renaming (MRN) mitigate load data…
We analyze the performance of a Brownian ratchet in the presence of geometrical constraints. A two-state model that describes the kinetics of molecular motors is used to characterize the energetic cost when the motor proceeds under…
We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…
We study the propagation and distribution of information-carrying signals injected in dynamical systems serving as a reservoir computers. A multivariate correlation analysis in tailored replica tests reveals consistency spectra and…
Throughput and energy efficiency in fading channels are studied in the presence of randomly arriving data and statistical queueing constraints. In particular, Markovian arrival models including discrete-time Markov, Markov fluid, and…
Lithium-ion technologies are increasingly employed to electrify transportation and provide stationary energy storage for electrical grids, and as such their development has garnered much attention. However, their deployment is still…
In the present study, we delineate the effect of introducing flow obstructions on streaming potential and energy conversion efficiency in a narrow fluidic confinement taking into consideration the wall hydrodynamic slip, finite ionic size,…
Energy consumption dictates the cost and environmental impact of deploying Large Language Models. This paper investigates the impact of on-chip SRAM size and operating frequency on the energy efficiency and performance of LLM inference,…
The increasing deployment of large language models (LLMs) in natural language processing (NLP) tasks raises concerns about energy efficiency and sustainability. While prior research has largely focused on energy consumption during model…
The performance and efficiency of distributed machine learning (ML) depends significantly on how long it takes for nodes to exchange state changes. Overly-aggressive attempts to reduce communication often sacrifice final model accuracy and…
Efficiently harvesting thermodynamic resources requires a precise understanding of their structure. This becomes explicit through the lens of information engines -- thermodynamic engines that use information as fuel. Maximizing the work…
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…