Related papers: A noise-tolerant, resource-saving probabilistic bi…

We study distributed algorithms implemented in a simplified biologically inspired model for stochastic spiking neural networks. We focus on tradeoffs between computation time and network complexity, along with the role of randomness in…

The mutual information of bit-interleaved coded modulation (BICM) systems, sometimes called the BICM capacity, is investigated at low signal-to-noise ratio (SNR), i.e., in the wideband regime. A new linear transform that depends on bits'…

Stochastic neurons are efficient hardware accelerators for solving a large variety of combinatorial optimization problems. "Binary" stochastic neurons (BSN) are those whose states fluctuate randomly between two levels +1 and -1, with the…

Quantum error mitigation (QEM) has emerged as a powerful tool for the extraction of useful quantum information from quantum devices. Here, we introduce the Subspace Noise Tailoring (SNT) algorithm, which efficiently combines the cheap cost…

With ultra-fast writing capacity and high reliability, the spin-orbit torque is regarded as a promising alternative to fabricate next-generation magnetic random access memory. However, the three-terminal setup can be challenging when…

Recently there has been increasing activity to build dedicated Ising Machines to accelerate the solution of combinatorial optimization problems by expressing these problems as a ground-state search of the Ising model. A common theme of such…

Using Resistive Random Access Memory (RRAM) crossbars in Computing-in-Memory (CIM) architectures offers a promising solution to overcome the von Neumann bottleneck. Due to non-idealities like cell variability, RRAM crossbars are often…

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…

Weight-sharing quantization has emerged as a technique to reduce energy expenditure during inference in large neural networks by constraining their weights to a limited set of values. However, existing methods for weight-sharing…

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…

We demonstrate for the first time full-scale integration of top-pinned perpendicular MTJ on 300 mm wafer using CMOS-compatible processes for spin-orbit torque (SOT)-MRAM architectures. We show that 62 nm devices with a W-based SOT…

The trade-off between computation time and path optimality is a key consideration in motion planning algorithms. While classical sampling based algorithms fall short of computational efficiency in high dimensional planning, learning based…

Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ…

The human brain is a complex spiking neural network (SNN), capable of learning multimodal signals in a zero-shot manner by generalizing existing knowledge. Remarkably, it maintains minimal power consumption through event-based signal…

In this paper, we propose a probabilistic parsing model, which defines a proper conditional probability distribution over non-projective dependency trees for a given sentence, using neural representations as inputs. The neural network…

Spin orbit torque (SOT) has been considered as one of the promising technologies for the next-generation magnetic random access memory (MRAM). So far, SOT has been widely utilized for inducing various modes of magnetization switching.…

Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are…

We have calculated the key characteristics of associative (content-addressable) spatial-temporal memories based on neuromorphic networks with restricted connectivity - "CrossNets". Such networks may be naturally implemented in…

Predicting chaotic systems is crucial for understanding complex behaviors, yet challenging due to their sensitivity to initial conditions and inherent unpredictability. Probabilistic Reservoir Computing (RC) is well-suited for long-term…

This paper explores methods for verifying the properties of Binary Neural Networks (BNNs), focusing on robustness against adversarial attacks. Despite their lower computational and memory needs, BNNs, like their full-precision counterparts,…