Related papers: Reliable Memories Built from Unreliable Components…

Graph Lottery Tickets (GLTs), comprising a sparse adjacency matrix and a sparse graph neural network (GNN), can significantly reduce the inference latency and compute footprint compared to their dense counterparts. Despite these benefits,…

Disaggregated memory architectures provide benefits to applications beyond traditional scale out environments, such as independent scaling of compute and memory resources. They also provide an independent failure model, where computations…

Second order stationary models in time series analysis are based on the analysis of essential statistics whose computations follow a common pattern. In particular, with a map-reduce nomenclature, most of these operations can be modeled as…

A recent paper by Gupta et al. (EuroSys'23) challenged the usefulness of trusted component (TC) based Byzantine fault-tolerant (BFT) protocols to lower the replica group size from $3f+1$ to $2f+1$, identifying three limitations of such…

Block Floating-Point (BFP) is emerging as an attractive data format for edge Neural Processing Units (NPUs), combining wide dynamic range with high hardware efficiency. However, its behavior under hardware faults and suitability for…

We study a new and stronger notion of fault-tolerant graph structures whose size bounds depend on the degree of the failing edge set, rather than the total number of faults. For a subset of faulty edges $F \subseteq G$, the faulty-degree…

We introduce Graph Memory (GM), a structured non-parametric framework that represents an embedding space through a compact graph of reliability-annotated prototype regions. GM encodes local geometry and regional ambiguity through prototype…

Presented below is an interesting type of associative memory called toggle memory based on the concept of T flip flops, as opposed to D flip flops. Toggle memory supports both reversible programming and charge recovery. Circuits designed…

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and…

In distributed storage systems built using commodity hardware, it is necessary to have data redundancy in order to ensure system reliability. In such systems, it is also often desirable to be able to quickly repair storage nodes that fail.…

Weak memory models are a consequence of the desire on part of architects to preserve all the uniprocessor optimizations while building a shared memory multiprocessor. The efforts to formalize weak memory models of ARM and POWER over the…

In this paper, we construct protograph-based spatially coupled low-density parity-check (SC-LDPC) codes by coupling together a series of L disjoint, or uncoupled, LDPC code Tanner graphs into a single coupled chain. By varying L, we obtain…

Deep learning models have been shown to be vulnerable to adversarial attacks. This perception led to analyzing deep learning models not only from the perspective of their performance measures but also their robustness to certain types of…

The brain, which uses redundancy and continuous learning to overcome the unreliability of its components, provides a promising path to building computing systems that are robust to the unreliability of their constituent nanodevices. In this…

Two classes of turbo codes over high-order finite fields are introduced. The codes are derived from a particular protograph sub-ensemble of the (dv=2,dc=3) low-density parity-check code ensemble. A first construction is derived as a…

With phenomenal growth of high speed and complex computing applications, the design of low power and high speed logic circuits have created tremendous interest. Conventional computing devices are based on irreversible logic and further…

The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the…

This paper explores the performance of fitted neural Q iteration for reinforcement learning in several partially observable environments, using three recurrent neural network architectures: Long Short-Term Memory, Gated Recurrent Unit and…

Neuromorphic architectures built with Non-Volatile Memory (NVM) can significantly improve the energy efficiency of machine learning tasks designed with Spiking Neural Networks (SNNs). A major source of voltage drop in a crossbar of these…

Machine unlearning poses the challenge of ``how to eliminate the influence of specific data from a pretrained model'' in regard to privacy concerns. While prior research on approximated unlearning has demonstrated accuracy and efficiency in…