Related papers: Information Density in Multi-Layer Resistive Memor…
The Information Bottleneck method is a learning technique that seeks a right balance between accuracy and generalization capability through a suitable tradeoff between compression complexity, measured by minimum description length, and…
Crossbar resistive memory with 1 Selector 1 Resistor (1S1R) structure is attractive for low-cost and high-density nonvolatile memory applications. As technology scales down to the single-nm regime, the increasing resistivity of…
We propose a scheme for multi-layer representation of images. The problem is first treated from an information-theoretic viewpoint where we analyze the behavior of different sources of information under a multi-layer data compression…
Optical phase-modulated fringe-patterns are usually digitized with XxY pixels and 8 bits/pixel (or higher) gray-levels. The digitized 8 bits/pixel are raw-data bits, not Shannon information bits. Here we show that noisy fringe-patterns…
The nonlinear response of driven complex materials -- disordered magnets, amorphous media, crumpled sheets -- features intricate transition pathways where the system repeatedly hops between metastable states. % which encode memory effects.…
The accelerating growth of global data generation demands data storage platforms that offer high capacity, long lifespan, and low energy consumption beyond the limits of electronic memory technologies. Optical storage provides an attractive…
We consider the problem of reliable communication over a discrete memoryless channel (DMC) with the help of a relay, termed the information bottleneck (IB) channel. There is no direct link between the source and the destination, and the…
High capacity and scalable memory systems play a vital role in enabling our desktops, smartphones, and pervasive technologies like Internet of Things (IoT). Unfortunately, memory systems are becoming increasingly prone to faults. This is…
DNA data storage systems encode digital data into DNA strands, enabling dense and durable storage. Efficient data retrieval depends on coverage depth, a key performance metric. We study the random access coverage depth problem and focus on…
We suggest a possible realization of a solid-state memory capacitive (memcapacitive) system. Our approach relies on the slow polarization rate of a medium between plates of a regular capacitor. To achieve this goal, we consider a…
Resistive random-access memory (RRAM) is gaining popularity due to its ability to offer computing within the memory and its non-volatile nature. The unique properties of RRAM, such as binary switching, multi-state switching, and device…
We consider a finite-state memoryless channel with i.i.d. channel state and the input Markov process supported on a mixing finite-type constraint. We discuss the asymptotic behavior of entropy rate of the output hidden Markov chain and…
Cells store information in DNA and in stable programs of gene expression, which thereby implement forms of long-term cellular memory. Cells must also possess short-term forms of information storage, implemented post-translationally, to…
In-memory computing is a promising alternative to traditional computer designs, as it helps overcome performance limits caused by the separation of memory and processing units. However, many current approaches struggle with unreliable…
We study various models of associative memories with sparse information, i.e. a pattern to be stored is a random string of $0$s and $1$s with about $\log N$ $1$s, only. We compare different synaptic weights, architectures and retrieval…
The increasing capacity of modern computers, driven by Moore's Law, is accompanied by smaller noise margins and higher error rates. In this paper we propose a memory device, consisting of a ring of two identical overdamped bistable…
The information bottleneck channel (or the oblivious relay channel) concerns a channel coding setting where the decoder does not directly observe the channel output. Rather, the channel output is relayed to the decoder by an oblivious relay…
We study finite sample expressivity, i.e., memorization power of ReLU networks. Recent results require $N$ hidden nodes to memorize/interpolate arbitrary $N$ data points. In contrast, by exploiting depth, we show that 3-layer ReLU networks…
Compression and efficient storage of neural network (NN) parameters is critical for applications that run on resource-constrained devices. Despite the significant progress in NN model compression, there has been considerably less…
Thermodynamic-driven filament formation in redox-based resistive memory and the impact of thermal fluctuations on switching probability of emerging magnetic switches are probabilistic phenomena in nature, and thus, processes of binary…