公开(公告)号：WO2011008973A9

公开(公告)日：2011-04-28

申请号：PCT/US2010042160

申请日：2010-07-15

Applicant: INTELLISIS CORP ,  LEWI JEREMY M

Inventor： LEWI JEREMY M

IPC: G06F9/455 ,  G06F15/18 ,  G06F17/10 ,  G06N3/12

CPC classification number: G06N3/02 ,  G06N3/10

Abstract: Disclosed are systems, apparatuses, and methods for implementing a phase-model neural network using a fixed amount of memory. Such a phase-model neural network includes a plurality of neurons, wherein each neuron is associated with two parameters-an activity and a phase. Example methods include (i) generating a sequence of variables associated with a probability distribution of phases and (ii) sequentially sampling the probability distribution of phases using a fixed amount of memory, regardless of a number of phases used in the phase-model neural network.

公开(公告)号：WO2011008973A2

公开(公告)日：2011-01-20

申请号：PCT/US2010/042160

申请日：2010-07-15

Applicant: THE INTELLISIS CORPORATION ,  LEWI, Jeremy, M.

Inventor： LEWI, Jeremy, M.

IPC: G06F9/455 ,  G06F17/10 ,  G06F15/18 ,  G06N3/12

CPC classification number: G06N3/10

Abstract: Disclosed are systems, apparatuses, and methods for implementing a phase- model neural network using a fixed amount of memory. Such a phase-model neural network includes a plurality of neurons, wherein each neuron is associated with two parameters — an activity and a phase. Example methods include (i) generating a sequence of variables associated with a probability distribution of phases and (ii) sequentially sampling the probability distribution of phases using a fixed amount of memory, regardless of a number of phases used in the phase-model neural network.

Abstract translation: 公开了使用固定量的存储器来实现相位模型神经网络的系统，装置和方法。 这样的相位模型神经网络包括多个神经元，其中每个神经元与两个参数 - 活动和相位相关联。 示例性方法包括（i）生成与相位的概率分布相关联的变量序列，以及（ii）使用固定量的存储器来顺序地采样相位的概率分布，而不管相位模型神经网络中使用的相位数 。