Parameter learning in a hidden trajectory model
    4.
    发明授权
    Parameter learning in a hidden trajectory model 有权
    隐藏轨迹模型中的参数学习

    公开(公告)号:US08942978B2

    公开(公告)日:2015-01-27

    申请号:US13182971

    申请日:2011-07-14

    IPC分类号: G10L15/00 G10L15/06

    CPC分类号: G10L15/063 G10L2015/025

    摘要: Parameters for distributions of a hidden trajectory model including means and variances are estimated using an acoustic likelihood function for observation vectors as an objection function for optimization. The estimation includes only acoustic data and not any intermediate estimate on hidden dynamic variables. Gradient ascent methods can be developed for optimizing the acoustic likelihood function.

    摘要翻译: 使用用于观察向量的声学似然函数作为优化的反对函数来估计包括装置和方差的隐藏轨迹模型的分布参数。 该估计仅包括声学数据,而不包括对隐藏的动态变量的任何中间估计。 可以开发梯度上升方法来优化声似然函数。

    Exploiting sparseness in training deep neural networks
    7.
    发明授权
    Exploiting sparseness in training deep neural networks 有权
    在深层神经网络训练中利用稀疏性

    公开(公告)号:US08700552B2

    公开(公告)日:2014-04-15

    申请号:US13305741

    申请日:2011-11-28

    IPC分类号: G06F15/18 G06N3/08

    CPC分类号: G06N3/08

    摘要: Deep Neural Network (DNN) training technique embodiments are presented that train a DNN while exploiting the sparseness of non-zero hidden layer interconnection weight values. Generally, a fully connected DNN is initially trained by sweeping through a full training set a number of times. Then, for the most part, only the interconnections whose weight magnitudes exceed a minimum weight threshold are considered in further training. This minimum weight threshold can be established as a value that results in only a prescribed maximum number of interconnections being considered when setting interconnection weight values via an error back-propagation procedure during the training. It is noted that the continued DNN training tends to converge much faster than the initial training.

    摘要翻译: 提出了深层神经网络(DNN)训练技术实施例,其训练DNN,同时利用非零隐藏层互连权重值的稀疏性。 通常,完全连接的DNN最初通过遍历完整的训练集多次进行训练。 那么,在大多数情况下,只有重量大小超过最小重量阈值的互连在进一步的训练中被考虑。 该最小权重阈值可以被建立为在训练期间通过错误反向传播过程设置互连权重值时仅考虑规定的最大数量的互连的值。 值得注意的是,继续进行的DNN训练往往比初始训练快得多。

    COMPUTER-IMPLEMENTED DEEP TENSOR NEURAL NETWORK
    8.
    发明申请
    COMPUTER-IMPLEMENTED DEEP TENSOR NEURAL NETWORK 有权
    计算机实现深度传感器神经网络

    公开(公告)号:US20140067735A1

    公开(公告)日:2014-03-06

    申请号:US13597268

    申请日:2012-08-29

    IPC分类号: G06N3/08

    摘要: A deep tensor neural network (DTNN) is described herein, wherein the DTNN is suitable for employment in a computer-implemented recognition/classification system. Hidden layers in the DTNN comprise at least one projection layer, which includes a first subspace of hidden units and a second subspace of hidden units. The first subspace of hidden units receives a first nonlinear projection of input data to a projection layer and generates the first set of output data based at least in part thereon, and the second subspace of hidden units receives a second nonlinear projection of the input data to the projection layer and generates the second set of output data based at least in part thereon. A tensor layer, which can converted into a conventional layer of a DNN, generates the third set of output data based upon the first set of output data and the second set of output data.

    摘要翻译: 本文描述了深张量神经网络(DTNN),其中DTNN适合于在计算机实现的识别/分类系统中的使用。 DTNN中的隐藏层包括至少一个投影层,其包括隐藏单元的第一子空间和隐藏单元的第二子空间。 隐藏单元的第一子空间至少部分地将输入数据的第一非线性投影接收到投影层,并且至少部分地生成第一组输出数据,并且隐藏单元的第二子空间接收输入数据的第二非线性投影 投影层并且至少部分地基于其生成第二组输出数据。 可以转换成DNN的常规层的张量层基于第一组输出数据和第二组输出数据产生第三组输出数据。

    Polymer containing thiophene unit and thienylenevinylene unit, and organic field effect transistor and organic solar cell containing the polymer
    9.
    发明授权
    Polymer containing thiophene unit and thienylenevinylene unit, and organic field effect transistor and organic solar cell containing the polymer 有权
    含有噻吩单元和噻吩乙烯单元的聚合物,以及含有聚合物的有机场效应晶体管和有机太阳能电池

    公开(公告)号:US08466239B2

    公开(公告)日:2013-06-18

    申请号:US12965068

    申请日:2010-12-10

    摘要: Provided are a polymer containing a thiophene unit and a thienylenevinylene unit, and an organic field effect transistor and an organic solar cell containing the polymer. The film may be formed by coating a substrate with a polymer containing a thiophene unit and a thienylenevinylene unit using a solution process. Therefore, the production cost may be reduced and a large-scale device may be suitably manufactured since there is no need for an expensive vacuum system to form films. Also, the polymer according to one embodiment of the present invention containing a thiophene unit and a thienylenevinylene unit has very excellent flatness since the thiophene unit is continuously coupled with a vinyl group having excellent flatness. Therefore, the polymer may be useful in further improving the charge mobility since it has high crystallinity caused by the improved ordering property between molecules. Such crystallinity may be further improved by the heat treatment. In addition, the organic compound according to one embodiment of the present invention containing a thienylenevinylene unit may have high oxidative stability because of its high ionization energy.

    摘要翻译: 提供含有噻吩单元和亚噻吩乙烯单元的聚合物,以及含有聚合物的有机场效应晶体管和有机太阳能电池。 可以通过使用溶液法用含有噻吩单元和噻吩乙炔单元的聚合物涂布基材来形成膜。 因此,由于不需要昂贵的真空系统来形成膜,所以可以降低生产成本并且可以适当地制造大型装置。 此外,根据本发明的一个实施方案,含有噻吩单元和亚噻吩基亚乙烯基单元的聚合物具有非常优异的平坦度,因为噻吩单元与具有优异平坦度的乙烯基连续地连接。 因此,由于分子之间的排序性能的改善,聚合物具有高的结晶度,所以可以进一步提高电荷迁移率。 通过热处理可以进一步提高这种结晶度。 此外,含有亚噻吩基亚乙烯基单元的本发明一个实施方案的有机化合物由于其高电离能而具有高的氧化稳定性。

    Automatic speech recognition learning using categorization and selective incorporation of user-initiated corrections
    10.
    发明授权
    Automatic speech recognition learning using categorization and selective incorporation of user-initiated corrections 有权
    自动语音识别学习使用分类和选择性并入用户发起的更正

    公开(公告)号:US08280733B2

    公开(公告)日:2012-10-02

    申请号:US12884434

    申请日:2010-09-17

    摘要: An automatic speech recognition system recognizes user changes to dictated text and infers whether such changes result from the user changing his/her mind, or whether such changes are a result of a recognition error. If a recognition error is detected, the system uses the type of user correction to modify itself to reduce the chance that such recognition error will occur again. Accordingly, the system and methods provide for significant speech recognition learning with little or no additional user interaction.

    摘要翻译: 自动语音识别系统识别用户对规定文本的改变,并且推测这种改变是否由用户改变主意而产生,或者这些改变是否是识别错误的结果。 如果检测到识别错误,则系统使用用户校正的类型进行自身修改,以减少再次发生这种识别错误的可能性。 因此,该系统和方法提供了很少或没有额外的用户交互的重要语音识别学习。