Related papers: Bayesian Reasoning Enabled by Spin-Orbit Torque Ma…
Continuous switching driven by spin-orbit torque (SOT) is preferred to realize neuromorphic computing in a spintronic manner. Here we have applied focused ion beam (FIB) to selectively illuminate patterned regions in a Pt/Co/MgO strip with…
This paper describes a new algorithm for exact Bayesian inference that is based on a recently proposed compositional semantics of Bayesian networks in terms of channels. The paper concentrates on the ideas behind this algorithm, involving a…
The paper introduces mixed networks, a new framework for expressing and reasoning with probabilistic and deterministic information. The framework combines belief networks with constraint networks, defining the semantics and graphical…
A Bayesian network is a widely used probabilistic graphical model with applications in knowledge discovery and prediction. Learning a Bayesian network (BN) from data can be cast as an optimization problem using the well-known…
Joint detection and estimation refers to deciding between two or more hypotheses and, depending on the test outcome, simultaneously estimating the unknown parameters of the underlying distribution. This problem is investigated in a…
In recent years, researchers in decision analysis and artificial intelligence (AI) have used Bayesian belief networks to build models of expert opinion. Using standard methods drawn from the theory of computational complexity, workers in…
We propose a new class of non-uniform superlattice magnetic tunnel junctions (Nu-SLTJs) with the Linear, Gaussian, Lorentzian, and P\"oschl-teller width and height based profiles manifesting a sizable enhancement in the TMR($\approx…
Bayesian networks provide a modeling language and associated inference algorithm for stochastic domains. They have been successfully applied in a variety of medium-scale applications. However, when faced with a large complex domain, the…
Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…
We investigate the stochastic dynamics of nanoscale perpendicular magnetic tunnel junctions (pMTJs) and the correlations that arise when they are electrically coupled. Individual junctions exhibit thermally activated spin-transfer torque…
When collaborating with an AI system, we need to assess when to trust its recommendations. If we mistakenly trust it in regions where it is likely to err, catastrophic failures may occur, hence the need for Bayesian approaches for…
Network inference has been extensively studied in several fields, such as systems biology and social sciences. Learning network topology and internal dynamics is essential to understand mechanisms of complex systems. In particular, sparse…
We use three-terminal magnetic tunnel junctions (MTJs) designed for field-free switching by spin-orbit torques (SOTs) to systematically study the impact of dual voltage pulses on the switching performances. We show that the concurrent…
Multiferroic tunnel junctions (MFTJs) have already been proved to be promising candidates for application in spintronics devices. The coupling between tunnel magnetoresistance (TMR) and tunnel electroresistance (TER) in MFTJs can provide…
Probabilistic Soft Logic has been proposed and used in several applications as an efficient way to deal with inconsistency, uncertainty and relational representation. In several applications, this approach has led to an adequate description…
Previous studies have demonstrated that encoding a Bayesian network into a SAT formula and then performing weighted model counting using a backtracking search algorithm can be an effective method for exact inference. In this paper, we…
Optimal Transport (OT) theory has seen an increasing amount of attention from the computer science community due to its potency and relevance in modeling and machine learning. It introduces means that serve as powerful ways to compare…
Causal inference using observational text data is becoming increasingly popular in many research areas. This paper presents the Bayesian Topic Regression (BTR) model that uses both text and numerical information to model an outcome…
The brain interprets ambiguous sensory information faster and more reliably than modern computers, using neurons that are slower and less reliable than logic gates. But Bayesian inference, which underpins many computational models of…
Machine learning implements backpropagation via abundant training samples. We demonstrate a multi-stage learning system realized by a promising non-volatile memory device, the domain-wall magnetic tunnel junction (DW-MTJ). The system…