公开(公告)号：WO2013081854A2

公开(公告)日：2013-06-06

申请号：PCT/US2012065502

申请日：2012-11-16

Applicant: IBM ,  EGYPT NANOTECHNOLOGY CT EGNC

Inventor： AFZALI-ARDAKANI ALI ,  HAN SHU-JEN ,  KASRY AMAL ,  MARTYNA GLENN J ,  NISTOR RAZVAN ,  TSAI HSINYU ,  MAAROUF AHMED

IPC: C40B40/04 ,  B82Y99/00 ,  C40B40/00 ,  C40B50/14

CPC classification number: G01N33/5308 ,  B82Y30/00 ,  B82Y40/00 ,  C01B32/194 ,  G01N33/54373 ,  G01N33/54393 ,  G01N33/551 ,  G01N2400/00

Abstract: A graphene nanomesh based charge sensor and method for producing a graphene nanomesh based charge sensor. The method includes generating multiple holes in graphene in a periodic way to create a graphene nanomesh with a patterned array of multiple holes, passivating an edge of each of the multiple holes of the graphene nanomesh to allow for functionalization of the graphene nanomesh, and functionalizing the passivated edge of each of the multiple holes of the graphene nanomesh with a chemical compound that facilitates chemical binding of a receptor of a target molecule to the edge of one or more of the multiple holes, allowing the target molecule to bind to the receptor, causing a charge to be transferred to the graphene nanomesh to produce a graphene nanomesh based charge sensor for the target molecule.

Abstract translation: 一种基于石墨烯纳米薄膜的电荷传感器和用于生产基于石墨烯纳米薄膜的电荷传感器的方法。 该方法包括以周期性方式在石墨烯中产生多个孔以产生具有多个孔的图案化阵列的石墨烯纳米粒子，钝化石墨烯纳米粒子的多个孔中的每一个的边缘以允许石墨烯纳米粒子的官能化，并使 石墨烯纳米粒子的多个孔的每个的钝化边缘具有促进靶分子的受体与多个孔中的一个或多个的边缘的化学结合的化学化合物，允许靶分子结合受体，导致 将转移到石墨烯纳米粒子的电荷以产生用于靶分子的基于石墨烯纳米膜的电荷传感器。

公开(公告)号：AU2021281628A1

公开(公告)日：2022-11-10

申请号：AU2021281628

申请日：2021-05-13

Applicant: IBM

Inventor： TSAI HSINYU ,  BURR GEOFFREY ,  NARAYANAN PRITISH

IPC: G06N3/063

Abstract: Implementing a convolutional neural network (CNN) includes configuring a crosspoint array to implement a convolution layer in the CNN. Convolution kernels of the layer are stored in crosspoint devices of the array. Computations for the CNN are performed by iterating a set of operations for a predetermined number of times. The operations include transmitting voltage pulses corresponding to a subpart of a vector of input data to the crosspoint array. The voltage pulses generate electric currents that are representative of performing multiplication operations at the crosspoint device based on weight values stored at the crosspoint devices. A set of integrators accumulates an electric charge based on the output electric currents from the respective crosspoint devices. The crosspoint array outputs the accumulated charge after iterating for the predetermined number of times. The accumulated charge represents a multiply-add result of the vector of input data and the one or more convolution kernels.

公开(公告)号：AU2021291671A1

公开(公告)日：2022-11-17

申请号：AU2021291671

申请日：2021-06-04

Applicant: IBM

Inventor： TSAI HSINYU ,  KARIYAPPA SANJAY

IPC: G06N3/10

Abstract: A drift regularization is provided to counteract variation in drift coefficients in analog neural networks. A method of training an artificial neural network is illustrated. A plurality of weights is randomly initialized. Each of the plurality of weights corresponds to a synapse of an artificial neural network. At least one array of inputs is inputted to the artificial neural network. At least one array of outputs is determined by the artificial neural network based on the at least one array of inputs and the plurality of weights. The at least one array of outputs is compared to ground truth data to determine a first loss. A second loss is determined by adding a drift regularization to the first loss. The drift regularization is positively correlated to variance of the at least one array of outputs. The plurality of weights is updated based on the second loss by backpropagation.