Related papers: Estimating the energy requirements for long term m…

Studies by microbiologists from the 1970s provided robust estimates for the energy supply and demand of a prokaryotic cell. The amount of ATP needed to support growth was calculated from the chemical composition of the cell and known…

The reliability of machine learning (ML) software systems is heavily influenced by changes in data over time. For that reason, ML systems require regular maintenance, typically based on model retraining. However, retraining requires…

With the growing adoption of AI image generation, in conjunction with the ever-increasing environmental resources demanded by AI, we are urged to answer a fundamental question: What is the environmental impact hidden behind each image we…

In many applications of evolutionary algorithms the computational cost of applying operators and storing populations is comparable to the cost of fitness evaluation. Furthermore, by knowing what exactly has changed in an individual by an…

LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled…

Efficient and compact neural network models are essential for enabling the deployment on mobile and embedded devices. In this work, we point out that typical design metrics for gauging the efficiency of neural network architectures -- total…

In the modern knowledge economy, success demands sustained focus and high cognitive performance. Research suggests that human cognition is linked to a finite resource, and upon its depletion, cognitive functions such as self-control and…

Associative memories are structures that store data in such a way that it can later be retrieved given only a part of its content -- a sort-of error/erasure-resilience property. They are used in applications ranging from caches and memory…

Energy costs of information processing are growing exponentially. Bit erasure is a key problem in this energy-information nexus, and a number of seminal relationships have been deduced regarding the relationship between thermodynamic costs…

Memorization impacts the performance of deep learning algorithms. Prior works have studied memorization primarily in the context of generalization and privacy. This work studies the memorization effect on incremental learning scenarios.…

Deficits in working memory, which includes both the ability to learn and to retain information short-term, are a hallmark of many cognitive disorders. Our study analyzes data from a neuroscience experiment on animal subjects, where…

Memories are stored, at least partly, as patterns of strong synapses. Given molecular turnover, how can synapses maintain strong for the years that memories can persist? Some models postulate that biochemical bistability maintains strong…

This paper presents a novel information-theoretic proof demonstrating that the human brain as currently understood cannot function as a classical digital computer. Through systematic quantification of distinguishable conscious states and…

Refresh is an important operation to prevent loss of data in dynamic random-access memory (DRAM). However, frequent refresh operations incur considerable power consumption and degrade system performance. Refresh power cost is especially…

Phase change memory (PCM) is one of the leading candidates for neuromorphic hardware and has recently matured as a storage class memory. Yet, energy and power consumption remain key challenges for this technology because part of the PCM…

Biological molecular machines are bifunctional enzymes that catalyze two processes: one donating free energy and the other accepting it. Recent studies show that most protein enzymes have rich stochastic dynamics of transitions between the…

Intelligence necessitates memory. Without memory, humans fail to perform various nontrivial tasks such as reading novels, playing games or solving maths. As the ultimate goal of machine learning is to derive intelligent systems that learn…

The memory hierarchy has a high impact on the performance and power consumption in the system. Moreover, current embedded systems, included in mobile devices, are specifically designed to run multimedia applications, which are memory…

Energy consumption in buildings, both residential and commercial, accounts for approximately 40% of all energy usage in the U.S., and similar numbers are being reported from countries around the world. This significant amount of energy is…

We report short-term memory formation in a nonlinear dynamical system with many degrees of freedom. The system ``remembers'' a sequence of impulses for a transient period, but it coarsens and eventually ``forgets'' nearly all of them. The…