利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.015 秒)

    APPARATUS AND METHOD FOR PARTIAL EVALUATION OF SYNAPTIC UPDATES BASED ON SYSTEM EVENTS
    2.
    发明申请
    APPARATUS AND METHOD FOR PARTIAL EVALUATION OF SYNAPTIC UPDATES BASED ON SYSTEM EVENTS 有权
    基于系统事件部分评估更新的装置和方法

    公开(公告)号：US20140372355A1

    公开(公告)日：2014-12-18

    申请号：US14275663

    申请日：2014-05-12

    申请人： BRAIN Corporation

    发明人： Eugene M. Izhikevich ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

    IPC分类号： G06N3/04 ,  G06N3/063

    CPC分类号： G06N3/049 ,  G06N3/063 ,  G06N3/08

    摘要： 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.

    摘要翻译： 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。

    Systems and methods for robust robotic mapping
    5.
    发明授权
    Systems and methods for robust robotic mapping 有权

    公开(公告)号：US11340630B2

    公开(公告)日：2022-05-24

    申请号：US15942123

    申请日：2018-03-30

    申请人： Brain Corporation

    发明人： Jayram Moorkanikara Nageswaran ,  Oleg Sinyavskiy ,  Borja Ibarz Gabardos

    IPC分类号： G05D1/02 ,  G05D1/00

    摘要： Systems and methods for robotic mapping are disclosed. In some example implementations, an automated device can travel in an environment. From travelling in the environment, the automated device can create a graph comprising a plurality of nodes, wherein each node corresponds to a scan taken by one or more sensors of the automated device at a location in the environment. In some example embodiments, the automated device can reevaluate its travel along a desired path if it encounters objects or obstructions along its path, whether those objects or obstructions are present in the front, rare or side of the automated device. In some example embodiments, the automated device uses a timestamp methodology to maneuver around its environment that provides faster processing and less usage of memory space.

    APPARATUS AND METHODS FOR EVENT-TRIGGERED UPDATES IN PARALLEL NETWORKS
    7.
    发明申请
    APPARATUS AND METHODS FOR EVENT-TRIGGERED UPDATES IN PARALLEL NETWORKS 有权
    并行网络中事件触发更新的设备和方法

    公开(公告)号：US20140250036A1

    公开(公告)日：2014-09-04

    申请号：US14198446

    申请日：2014-03-05

    申请人： BRAIN CORPORATION

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

    IPC分类号： G06N3/10

    CPC分类号： G06N3/08 ,  G05B13/027 ,  G06N3/049 ,  G06N3/10

    摘要： 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.

    摘要翻译： 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。

    SYSTEMS AND METHODS FOR ROBUST ROBOTIC MAPPING
    9.
    发明申请
    SYSTEMS AND METHODS FOR ROBUST ROBOTIC MAPPING 审中-公开

    公开(公告)号：US20190302791A1

    公开(公告)日：2019-10-03

    申请号：US15942123

    申请日：2018-03-30

    申请人： Brain Corporation

    发明人： Jayram Moorkanikara Nageswaran ,  Oleg Sinyavskiy ,  Borja Ibarz Gabardos

    IPC分类号： G05D1/02 ,  G05D1/00

    摘要： Systems and methods for robotic mapping are disclosed. In some example implementations, an automated device can travel in an environment. From travelling in the environment, the automated device can create a graph comprising a plurality of nodes, wherein each node corresponds to a scan taken by one or more sensors of the automated device at a location in the environment. In some example embodiments, the automated device can reevaluate its travel along a desired path if it encounters objects or obstructions along its path, whether those objects or obstructions are present in the front, rare or side of the automated device. In some example embodiments, the automated device uses a timestamp methodology to maneuver around its environment that provides faster processing and less usage of memory space.