公开(公告)号：US09147156B2

公开(公告)日：2015-09-29

申请号：US13239255

申请日：2011-09-21

Applicant: Eugene M. Izhikevich ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran ,  Jeffrey Alexander Levin ,  Venkat Rangan ,  Erik Christopher Malone

Inventor： Eugene M. Izhikevich ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran ,  Jeffrey Alexander Levin ,  Venkat Rangan ,  Erik Christopher Malone

IPC: G06F1/16 ,  G06N3/04

CPC classification number: G06N3/049

Abstract: Apparatus and methods for efficient synaptic update in a network such as a spiking neural network. In one embodiment, the post-synaptic updates, in response to generation of a post-synaptic pulse by a post-synaptic unit, are delayed until a subsequent pre-synaptic pulse is received by the unit. Pre-synaptic updates are performed first following by the post-synaptic update, thus ensuring synaptic connection status is up-to-date. The delay update mechanism is used in conjunction with system “flush” events in order to ensure accurate network operation, and prevent loss of information under a variety of pre-synaptic and post-synaptic unit firing rates. A large network partition mechanism is used in one variant with network processing apparatus in order to enable processing of network signals in a limited functionality embedded hardware environment.

Abstract translation: 用于在诸如尖峰神经网络的网络中有效突触更新的装置和方法。 在一个实施例中，响应于由突触后单元产生后突触脉冲的突触后更新被延迟，直到该单元接收到后续的突触前脉冲。 先突触后更新是在突触后更新之后进行的，因此确保突触连接状态是最新的。 延迟更新机制与系统“刷新”事件结合使用，以确保网络运行准确，防止各种突触前和突触后单位发射速率下的信息丢失。 在一个变型中，网络分割机制用于网络处理设备，以便能够在有限的功能嵌入式硬件环境中处理网络信号。

公开(公告)号：US09224090B2

公开(公告)日：2015-12-29

申请号：US13465903

申请日：2012-05-07

Applicant: Filip Piekniewski ,  Eugene Izhikevich ,  Botond Szatmary ,  Csaba Petre

Inventor： Filip Piekniewski ,  Eugene Izhikevich ,  Botond Szatmary ,  Csaba Petre

IPC: G06N3/04

CPC classification number: G06N3/04 ,  G06N3/049 ,  G06N3/088

Abstract: Apparatus and methods for feedback in a spiking neural network. In one approach, spiking neurons receive sensory stimulus and context signal that correspond to the same context. When the stimulus provides sufficient excitation, neurons generate response. Context connections are adjusted according to inverse spike-timing dependent plasticity. When the context signal precedes the post synaptic spike, context synaptic connections are depressed. Conversely, whenever the context signal follows the post synaptic spike, the connections are potentiated. The inverse STDP connection adjustment ensures precise control of feedback-induced firing, eliminates runaway positive feedback loops, enables self-stabilizing network operation. In another aspect of the invention, the connection adjustment methodology facilitates robust context switching when processing visual information. When a context (such an object) becomes intermittently absent, prior context connection potentiation enables firing for a period of time. If the object remains absent, the connection becomes depressed thereby preventing further firing.

Abstract translation: 用于在加标神经网络中反馈的装置和方法。 在一种方法中，刺激神经元接收对应于相同上下文的感觉刺激和上下文信号。 当刺激提供足够的激发时，神经元产生反应。 上下文连接根据反时限相关的可塑性进行调整。 当上下文信号在后突触尖端之前时，上下文突触连接被按下。 相反，只要上下文信号跟随突触后的尖峰，连接就被加强了。 反向STDP连接调整可确保对反馈引发的精确控制，消除失控的正反馈回路，实现自稳定网络运行。 在本发明的另一方面，当处理视觉信息时，连接调整方法有助于鲁棒的上下文切换。 当上下文（这样的对象）间歇地不存在时，先前的上下文连接增强使得能够触发一段时间。 如果物体不存在，则连接被压下，从而防止进一步的烧制。

公开(公告)号：US08719199B2

公开(公告)日：2014-05-06

申请号：US13239163

申请日：2011-09-21

Applicant: Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

Inventor： Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

IPC: G05B13/02 ,  G06N3/08

CPC classification number: G06N3/08 ,  G05B13/027 ,  G06N3/049 ,  G06N3/10

Abstract: A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. The software and hardware engines are optimized to take into account short-term and long-term synaptic plasticity in the form of LTD, LTP, and STDP.

Abstract translation: 公开了一种简单的格式，并被称为基本网络描述（END）。 该格式可以充分描述大规模神经元模型和软件或硬件引擎的实施例，以有效地模拟这种模型。 这种神经形态发动机的架构对于具有尖峰时间依赖可塑性的加标网络的高性能并行处理是最佳的。 软件和硬件引擎经过优化考虑了LTD，LTP和STDP形式的短期和长期突触可塑性。

公开(公告)号：US20130297539A1

公开(公告)日：2013-11-07

申请号：US13465918

申请日：2012-05-07

Applicant: Filip Piekniewski ,  Eugene Izhikevich ,  Botond Szatmary ,  Csaba Petre

Inventor： Filip Piekniewski ,  Eugene Izhikevich ,  Botond Szatmary ,  Csaba Petre

IPC: G06N3/02

CPC classification number: G06N3/049

Abstract: Apparatus and methods for feedback in a spiking neural network. In one approach, spiking neurons receive sensory stimulus and context signal that correspond to the same context. When the stimulus provides sufficient excitation, neurons generate response. Context connections are adjusted according to inverse spike-timing dependent plasticity. When the context signal precedes the post synaptic spike, context synaptic connections are depressed. Conversely, whenever the context signal follows the post synaptic spike, the connections are potentiated. The inverse STDP connection adjustment ensures precise control of feedback-induced firing, eliminates runaway positive feedback loops, enables self-stabilizing network operation. In another aspect of the invention, the connection adjustment methodology facilitates robust context switching when processing visual information. When a context (such an object) becomes intermittently absent, prior context connection potentiation enables firing for a period of time. If the object remains absent, the connection becomes depressed thereby preventing further firing.

Abstract translation: 用于在加标神经网络中反馈的装置和方法。 在一种方法中，刺激神经元接收对应于相同上下文的感觉刺激和上下文信号。 当刺激提供足够的激发时，神经元产生反应。 上下文连接根据反时限相关的可塑性进行调整。 当上下文信号在后突触尖端之前时，上下文突触连接被按下。 相反，只要上下文信号跟随突触后的尖峰，连接就被加强了。 反向STDP连接调整可确保对反馈引发的精确控制，消除失控的正反馈回路，实现自稳定网络运行。 在本发明的另一方面，当处理视觉信息时，连接调整方法有助于鲁棒的上下文切换。 当上下文（这样的对象）间歇地不存在时，先前的上下文连接增强使得能够触发一段时间。 如果物体不存在，则连接被压下，从而防止进一步的烧制。

公开(公告)号：US20130073484A1

公开(公告)日：2013-03-21

申请号：US13239155

申请日：2011-09-21

Applicant: Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski

Inventor： Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski

IPC: G06N3/04

CPC classification number: G06N3/10 ,  G06N3/04 ,  G06N3/049

Abstract: A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. Methods for managing memory in a processing system are described whereby memory can be allocated among a plurality of elements and rules configured for each element such that the parallel execution of the spiking networks is most optimal.

Abstract translation: 公开了一种简单的格式，并被称为基本网络描述（END）。 该格式可以充分描述大规模神经元模型和软件或硬件引擎的实施例，以有效地模拟这种模型。 这种神经形态发动机的架构对于具有尖峰时间依赖可塑性的加标网络的高性能并行处理是最佳的。 描述了用于管理处理系统中的存储器的方法，其中可以在为每个元件配置的多个元件和规则之间分配存储器，使得加标网络的并行执行是最佳的。

公开(公告)号：US09117176B2

公开(公告)日：2015-08-25

申请号：US13385937

申请日：2012-03-15

Applicant: Botond Szatmary ,  Eugene M. Izhikevich ,  Csaba Petre ,  Jayram Moorkanikara Nageswaran ,  Filip Piekniewski

Inventor： Botond Szatmary ,  Eugene M. Izhikevich ,  Csaba Petre ,  Jayram Moorkanikara Nageswaran ,  Filip Piekniewski

IPC: G06N7/00 ,  G06N3/08 ,  G06N3/10 ,  G06F9/44

CPC classification number: G06N3/08 ,  G06F8/355 ,  G06N3/10

Abstract: Apparatus and methods for high-level neuromorphic network description (HLND) framework that may be configured to enable users to define neuromorphic network architectures using a unified and unambiguous representation that is both human-readable and machine-interpretable. The framework may be used to define nodes types, node-to-node connection types, instantiate node instances for different node types, and to generate instances of connection types between these nodes. To facilitate framework usage, the HLND format may provide the flexibility required by computational neuroscientists and, at the same time, provides a user-friendly interface for users with limited experience in modeling neurons. The HLND kernel may comprise an interface to Elementary Network Description (END) that is optimized for efficient representation of neuronal systems in hardware-independent manner and enables seamless translation of HLND model description into hardware instructions for execution by various processing modules.

Abstract translation: 用于高级神经形态网络描述（HLND）框架的装置和方法，其可以被配置为使得用户能够使用统一且明确的表示来定义神经形态网络架构，其是可读和机器可解释的。 该框架可用于定义节点类型，节点到节点连接类型，不同节点类型的实例化节点实例，以及生成这些节点之间连接类型的实例。 为了促进框架使用，HLND格式可以提供计算神经科学家所需的灵活性，并且同时为具有有限的神经元建模经验的用户提供用户友好的界面。 HLND内核可以包括到基本网络描述（END）的接口，其被优化用于以与硬件无关的方式有效地表示神经元系统，并且能够将HLND模型描述无缝地转换成硬件指令以供各种处理模块执行。

公开(公告)号：US08725662B2

公开(公告)日：2014-05-13

申请号：US13239259

申请日：2011-09-21

Applicant: Eugene M. Izhikevich ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

Inventor： Eugene M. Izhikevich ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

IPC: G06N3/08

CPC classification number: G06N3/049 ,  G06N3/063 ,  G06N3/08

Abstract: Apparatus and methods for partial evaluation of synaptic updates in neural networks. In one embodiment, a pre-synaptic unit is connected to a several post synaptic units via communication channels. Information related to a plurality of post-synaptic pulses generated by the post-synaptic units is stored by the network in response to a system event. Synaptic channel updates are performed by the network using the time intervals between a pre-synaptic pulse, which is being generated prior to the system event, and at least a portion of the plurality of the post synaptic pulses. The system event enables removal of the information related to the portion of the post-synaptic pulses from the storage device. A shared memory block within the storage device is used to store data related to post-synaptic pulses generated by different post-synaptic nodes. This configuration enables memory use optimization of post-synaptic units with different firing rates.

Abstract translation: 用于部分评估神经网络中突触更新的装置和方法。 在一个实施例中，突触前单元经由通信信道连接到几个后突触单元。 与由突触后单元生成的多个突触后脉冲相关的信息由网络响应于系统事件存储。 突触信道更新由网络使用在系统事件之前产生的预触觉脉冲与多个突触后脉冲的至少一部分之间的时间间隔来执行。 系统事件使得能够从存储设备去除与突触后部分脉冲相关的信息。 存储设备内的共享存储器块用于存储与由不同的突触后节点产生的突触后脉冲相关的数据。 这种配置使得具有不同发射速率的突触后单元的存储器使用优化成为可能。

公开(公告)号：US08725658B2

公开(公告)日：2014-05-13

申请号：US13239155

申请日：2011-09-21

Applicant: Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski

Inventor： Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski

IPC: G06F19/12 ,  G06N3/10 ,  G06N3/04

CPC classification number: G06N3/10 ,  G06N3/04 ,  G06N3/049

Abstract: A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. Methods for managing memory in a processing system are described whereby memory can be allocated among a plurality of elements and rules configured for each element such that the parallel execution of the spiking networks is most optimal.

Abstract translation: 公开了一种简单的格式，并被称为基本网络描述（END）。 该格式可以充分描述大规模神经元模型和软件或硬件引擎的实施例，以有效地模拟这种模型。 这种神经形态发动机的架构对于具有尖峰时间依赖可塑性的加标网络的高性能并行处理是最佳的。 描述了用于管理处理系统中的存储器的方法，其中可以在为每个元件配置的多个元件和规则之间分配存储器，使得加标网络的并行执行是最佳的。

公开(公告)号：US20130073492A1

公开(公告)日：2013-03-21

申请号：US13239163

申请日：2011-09-21

Applicant: Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

Inventor： Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

IPC: G05B13/02

CPC classification number: G06N3/08 ,  G05B13/027 ,  G06N3/049 ,  G06N3/10

Abstract: A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. The software and hardware engines are optimized to take into account short-term and long-term synaptic plasticity in the form of LTD, LTP, and STDP.

Abstract translation: 公开了一种简单的格式，并被称为基本网络描述（END）。 该格式可以充分描述大规模神经元模型和软件或硬件引擎的实施例，以有效地模拟这种模型。 这种神经形态发动机的架构对于具有尖峰时间依赖可塑性的加标网络的高性能并行处理是最佳的。 软件和硬件引擎经过优化考虑了LTD，LTP和STDP形式的短期和长期突触可塑性。

公开(公告)号：US09111215B2

公开(公告)日：2015-08-18

申请号：US13541531

申请日：2012-07-03

Applicant: Filip Piekniewski

Inventor： Filip Piekniewski

IPC: G06N3/02 ,  G06N3/04

CPC classification number: G06N3/02 ,  G06N3/049

Abstract: Apparatus and methods for conditional plasticity in a neural network. In one approach, conditional plasticity mechanism is configured to select alternate plasticity rules when performing connection updates. The selection mechanism is adapted based on a comparison of actual connection efficiency and target efficiency. For instance, when actual efficiency is below the target value, the STDP rule may be modulated to increase long term potentiation. Similarly, when actual efficiency is above the target value, the STDP rule may be modulated to increase long term connection depression. The conditional plasticity mechanism dynamically adjusts connection efficacy, and prevents uncontrolled increase of connection weights, thereby improving network operation when processing information of a varying nature.

Abstract translation: 神经网络条件可塑性的装置和方法。 在一种方法中，条件可塑性机制被配置为在执行连接更新时选择替代塑性规则。 基于实际连接效率和目标效率的比较来选择机制。 例如，当实际效率低于目标值时，可以调制STDP规则以增加长期增强。 类似地，当实际效率高于目标值时，可以调制STDP规则以增加长期连接抑制。 条件可塑性机制动态调整连接效能，并防止连接权重的不受控制的增加，从而在处理不同性质的信息时改善网络操作。