公开(公告)号：US20230297883A1

公开(公告)日：2023-09-21

申请号：US18016833

申请日：2020-10-13

Applicant: TDK CORPORATION

Inventor： Kazuki NAKADA

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A discriminator includes: a filter bank having a response characteristic to a signal with a specific waveform and including a plurality of matched filters transforming a time-series input signal into a plurality of features in accordance with the response characteristic; a softmax function configured to accept the plurality of features and transform the plurality of features into a probability distribution; and a loss function configured to obtain a cross-entropy loss between the probability distribution and a class label. The parameter of each of the plurality of matched filters is adjusted based on the cross-entropy loss.

公开(公告)号：US20230140456A1

公开(公告)日：2023-05-04

申请号：US17910694

申请日：2020-03-26

Applicant: TDK CORPORATION

Inventor： Kazuki NAKADA

IPC: G06N7/01 ,  H04R19/04 ,  H04R3/00

Abstract: A parameter distribution setting method including performs learning based on a gradient learning method in advance such that a mutual information between a probabilistic distribution of an output of a reservoir device and an ideal probabilistic distribution of the output increases, and setting a parameter distribution of parameters defining element derivation in a plurality of elements constituting the reservoir device in a device model for the reservoir device.

公开(公告)号：US20220180160A1

公开(公告)日：2022-06-09

申请号：US17441761

申请日：2019-03-27

Applicant: TDK CORPORATION

Inventor： Kazuki NAKADA

IPC: G06N3/063 ,  G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: An outlier detection device includes a reservoir computer having an input layer, a reservoir main unit including neurons connected by synapses, and a read-out configured to calculate and output an inner product of a weight vector and an activity value vector, each element of which is an activity value output from each of neurons based on an input to the input layer, a learning unit configured to acquire an observed signal, calculate an error between the inner product and the observed signal, and update the weight vector using a value obtained by applying an adaptive filter to the error, a norm calculation unit configured to sequentially calculate a norm of the weight vector updated by the learning unit, and a determination unit configured to determine whether an outlier is included in the observed signal based on at least one of the norms calculated by the norm calculation unit.

公开(公告)号：US20220114418A1

公开(公告)日：2022-04-14

申请号：US17558129

申请日：2021-12-21

Applicant: TDK CORPORATION

Inventor： Kazuki NAKADA

IPC: G06N3/04

Abstract: A machine learning device performing online learning of input data of one or more dimensions aligned in a pre-determined order using a recurrent neural network having a plurality of nodes connected by edges to which weights are assigned performs an output data generating process and a weight updating process every time the input layer receives the input data of one or more dimensions in the pre-determined order, in which, the weight updating process is a process in which a weight assigned to each edge connecting a 1st intermediate node and a 2nd intermediate node and a weight assigned to each edge connecting a 2nd intermediate node and an output node are updated using an equation derived based on an extended Kalman filter method, 1st intermediate data of one or more dimensions, and output data of one or more dimensions.

公开(公告)号：US20240311629A1

公开(公告)日：2024-09-19

申请号：US18121302

申请日：2023-03-14

Applicant: TDK CORPORATION

Inventor： Kazuki NAKADA

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: An online learning method includes: compressing a range of possible values of a Kalman gain before an update; obtaining a Kalman gain after the update from the compressed Kalman gain before the update using an expanded Kalman filter method; expanding the range of possible values of the Kalman gain after the update, and updating a weight by adding a weight before the update to a result obtained by multiplying the Kalman gain in which the range of the possible values of the Kalman gain is expanded by an error between a training signal and an inference result in which a weight before the update is used.

公开(公告)号：US20230419094A1

公开(公告)日：2023-12-28

申请号：US18039561

申请日：2020-12-03

Applicant: TDK CORPORATION

Inventor： Kazuki NAKADA

IPC: G06N3/065 ,  G06N3/044 ,  G06N3/084

CPC classification number: G06N3/065 ,  G06N3/044 ,  G06N3/084

Abstract: A reservoir element according to an embodiment is a reservoir element including a ring-shaped reservoir constituted by a single nonlinear element and a plurality of delay elements, in which the nonlinear element has a nonlinear modulation function, the nonlinear element being controllable by a time-varying parameter capable of dynamically changing the nonlinear modulation function, and the reservoir element includes a control unit that controls the time-varying parameter in accordance with a time series having a cycle corresponding to the number of stages of the nonlinear element and the delay elements.

公开(公告)号：US20220309339A1

公开(公告)日：2022-09-29

申请号：US17496934

申请日：2021-10-08

Applicant: TDK CORPORATION

Inventor： Yukio TERASAKI ,  Kazuki NAKADA

IPC: G06N3/08 ,  G06N3/063 ,  G06N3/04

Abstract: An information processing device includes a reservoir layer, and a read-out layer. The reservoir layer includes a plurality of nodes that generate a feature space including information of an input signal input to the reservoir layer, the read-out layer performs an operation of applying a connection weight to each of signals sent from the reservoir layer, and the number of signals sent to the read-out layer from the reservoir layer is smaller than the number of the plurality of nodes.

公开(公告)号：US20220171603A1

公开(公告)日：2022-06-02

申请号：US17439992

申请日：2019-03-19

Applicant: TDK CORPORATION

Inventor： Kazuki NAKADA

IPC: G06F7/544

Abstract: A multiply-accumulate calculation device includes a plurality of redundancy circuits including a plurality of multiply calculation elements and configured to input a plurality of first intermediate signals generated from an input signal corresponding to an input value to the plurality of multiply calculation elements and generate and output a plurality of second intermediate signals, each of which corresponds to a signal obtained by multiplying each of the plurality of first intermediate signals by a weight in each of the plurality of multiply calculation elements, a plurality of output signal generation circuits configured to generate output signals on the basis of the plurality of second intermediate signals and output the output signals, and an accumulate calculation circuit configured to calculate a sum of the output signals output by the plurality of output signal generation circuits.

公开(公告)号：US20210263884A1

公开(公告)日：2021-08-26

申请号：US17111934

申请日：2020-12-04

Applicant: TDK CORPORATION

Inventor： Kazuki NAKADA

IPC: G06F15/82 ,  G06F30/20

Abstract: A reservoir computing data flow processor includes a plurality of reservoir units to be units constituting a reservoir. The reservoir is able to be reconfigured by changing a connection relationship between the reservoir units. Each of the reservoir units is an operation unit block configured to execute a predetermined operation. The operation unit block includes a first adder configured to perform an addition operation on at least two inputs, a nonlinear operator configured to apply a nonlinear function to an output from the first adder or a result of multiplying the output by a predetermined coefficient, and a second adder configured to perform an addition operation on at least two inputs including an output from the nonlinear operator or a result of multiplying the output by a predetermined coefficient.