Bayesian reasoning machine on a magneto-tunneling junction network
Bayesian reasoning machine on a magneto-tunneling junction network
复制标题
磁隧道连接网络上的贝叶斯推理机
DOI：
10.1088/1361-6528/abae97
复制
发表时间：
2020
期刊：
影响因子：
3.5
通讯作者：
Trivedi, Amit Ranjan
中科院分区：
文献类型：
--
作者：
Nasrin, Shamma;Drobitch, Justine;Shukla, Priyesh;Tulabandhula, Theja;Bandyopadhyay, Supriyo;Trivedi, Amit Ranjan
最近的趋势，在适应超节能（但容易出错）的纳米磁性设备的非布尔计算和信息处理（如随机/概率计算，神经形态，信念网络等），导致了新的计算模式的快速发展。特别令人感兴趣的是贝叶斯网络（BN），当适应特定类型的纳米磁性设备时，它可能会看到革命性的进步。在这里，我们开发了一种新的基于纳米磁体的BN计算基板，允许从任意贝叶斯图进行高速采样。我们表明，磁隧道结（MTJ）可用于电可编程的“亚纳秒”概率样本生成通过共同优化电压控制的磁各向异性和自旋转移矩。我们还讨论了，只是通过工程的软层的MTJ的局部磁致伸缩，可以随机耦合，以及可编程的条件样本生成。这避免了需要大量的低能效硬件，如运算放大器，门，移位寄存器等来生成相关性。基于上述研究结果，我们提出了一个架构设计和计算流程的MTJ网络映射任意贝叶斯图，我们开发电路编程和诱导MTJ之间的切换和相互作用。我们讨论的框架可以为各种其他计算模型（如随机编程和贝叶斯深度学习）带来新一代的随机计算硬件。这可以催生一种超节能、极其强大的计算模式，这是一种变革性的进步。
The recent trend in adapting ultra-energy-efficient (but error-prone) nanomagnetic devices to non-Boolean computing and information processing (eg stochastic/probabilistic computing, neuromorphic, belief networks, etc) has resulted in rapid strides in new computing modalities. Of particular interest are Bayesian networks (BN) which may see revolutionary advances when adapted to a specific type of nanomagnetic devices. Here, we develop a novel nanomagnet-based computing substrate for BN that allows high-speed sampling from an arbitrary Bayesian graph. We show that magneto-tunneling junctions (MTJs) can be used for electrically programmable'sub-nanosecond'probability sample generation by co-optimizing voltage-controlled magnetic anisotropy and spin transfer torque. We also discuss that just by engineering local magnetostriction in the soft layers of MTJs, one can stochastically couple them for programmable conditional sample generation as well. This obviates the need for extensive energy-inefficient hardware like OP-AMPS, gates, shift-registers, etc to generate the correlations. Based on the above findings, we present an architectural design and computation flow of the MTJ network to map an arbitrary Bayesian graph where we develop circuits to program and induce switching and interactions among MTJs. Our discussed framework can lead to a new generation of stochastic computing hardware for various other computing models, such as stochastic programming and Bayesian deep learning. This can spawn a novel genre of ultra-energy-efficient, extremely powerful computing paradigms, which is a transformational advance.
登录
查看更多内容
影响因子：
20.6
作者：
Camsari, Kerem Y.;Debashis, Punyashloka;Appenzeller, Joerg
通讯作者：
Appenzeller, Joerg
基于混合模式磁隧道结的深度置信网络
DOI：
10.1109/nano46743.2019.8993914
发表时间：
2019
期刊：
2019 IEEE 19th International Conference on Nanotechnology (IEEE-NANO)
影响因子：
--
作者：
Shamma Nasrin;J. Drobitch;Supriyo Bandyopadhyay;A. Trivedi
通讯作者：
A. Trivedi
影响因子：
1.5
作者：
J. Drobitch;Ahsanul Abeed;Supriyo Bandyopadhyay
通讯作者：
J. Drobitch;Ahsanul Abeed;Supriyo Bandyopadhyay
适用于嘈杂物联网场景的贝叶斯数据包共享方法
DOI：
--
发表时间：
2016
期刊：
International Conference on Internet-of-Things Design and Implementation
影响因子：
--
作者：
A. Vegni;V. Loscrí;A. Neri;Marco Leo
通讯作者：
Marco Leo
影响因子：
10.6
作者：
Joseph Siryani;Bereket Tanju;T. Eveleigh
通讯作者：
Joseph Siryani;Bereket Tanju;T. Eveleigh