Neuromorphic architecture for feature learning using a spiking neural network

    公开(公告)号:US11080592B2

    公开(公告)日:2021-08-03

    申请号:US15725320

    申请日:2017-10-05

    IPC分类号: G06N3/04 G06N20/00

    摘要: A neuromorphic architecture for a spiking neural network comprising a plurality of spiking neurons, each with a plurality of synapses and corresponding synaptic weights, the architecture further comprising a synaptic competition mechanism in connection with a spike-based learning mechanism based on spikes perceived behind a synapse, in which architecture synapses of different neurons connected to the same input compete for that input and based on the result of that competition, each neuron of the neural network develops an individual perception of the presented input spikes, the perception used by the learning mechanism to adjust the synaptic weights.

    Characterization of nonlinearity in servo patterns

    公开(公告)号:US10657997B2

    公开(公告)日:2020-05-19

    申请号:US16398030

    申请日:2019-04-29

    IPC分类号: G11B5/55 G11B5/588 G11B5/008

    摘要: A method according to one embodiment includes applying a static head skew to a magnetic tape head, positioning the first reader at a first y-position relative to a servo pattern in a servo band, and measuring y-positions of the second reader relative to the servo pattern in the servo band while the first reader is at the first y-position. A y-position value is calculated for the second reader based on the measured y-positions. The following process is repeated several times: moving the first reader to a next y-position, measuring y-positions of the second reader while the first reader is at the next y-position, and calculating a y-position value of the second reader based on the measured y-position of the second reader. A unique nonlinearity value of the servo pattern in the servo band is calculated for each of the calculated y-position values of the second reader.

    ARTIFICIAL NEURON APPARATUS
    23.
    发明申请

    公开(公告)号:US20190272464A1

    公开(公告)日:2019-09-05

    申请号:US16388121

    申请日:2019-04-18

    IPC分类号: G06N3/063 G06N3/04

    摘要: Artificial neuron apparatus includes first and second resistive memory cells. The first resistive memory cell is connected in first circuitry having a first input and output. The second resistive memory cell is connected in second circuitry having a second input and output. The first and second circuitry are operable in alternating read and write phases to apply a programming current to their respective memory cells on receipt of excitatory and inhibitory neuron input signals, respectively. During the write phase, resistance of the respective cells is changed in response to successive excitatory and inhibitory neuron input signals. During the read phase, a read current is applied to their respective cells to produce first and second measurement signals, respectively. An output circuit connected to the first and second outputs produces a neuron output signal at a neuron output when a difference between the first and second measurement signals traverses a threshold.

    Characterization of nonlinearity in servo patterns

    公开(公告)号:US10366716B1

    公开(公告)日:2019-07-30

    申请号:US16044396

    申请日:2018-07-24

    摘要: In one general embodiment, a method includes applying a static head skew to a magnetic tape head, positioning the first reader at a first y-position relative to a servo pattern in a servo band, measuring y-positions of the second reader relative to the servo pattern in the servo band while the first reader is at the first y-position, and averaging the measured y-positions. The method further includes repeating the following process several times: moving the first reader to a next y-position, measuring y-positions of the second reader while the first reader is at the next y-position, and averaging the y-positions measured by the second reader while the first reader is at the next y-position. The method further includes calculating a unique nonlinearity value of the servo pattern in the servo band for each of the average y-position values, and storing and/or outputting the calculated nonlinearity values.

    Artificial neuron apparatus
    25.
    发明授权

    公开(公告)号:US10268949B2

    公开(公告)日:2019-04-23

    申请号:US15075314

    申请日:2016-03-21

    IPC分类号: G06N3/063 G06N3/04

    摘要: Artificial neuron apparatus includes a resistive memory cell connected in an input circuit having a neuron input, for receiving neuron input signals, and a current source for supplying a read current to the cell. The input circuit is selectively configurable in response to a set of control signals, defining alternating read and write phases of operation, to apply the read current to the cell during the read phase and to apply a programming current to the cell, for programming cell resistance, on receipt of a neuron input signal during the write phase. The cell resistance is progressively changed from a first state to a second state in response to successive neuron input signals. The apparatus further includes an output circuit comprising a neuron output and a digital latch which is connected to the input circuit for receiving a measurement signal dependent on cell resistance.

    NEUROMORPHIC PROCESSING APPARATUS
    26.
    发明申请

    公开(公告)号:US20190057301A1

    公开(公告)日:2019-02-21

    申请号:US15680140

    申请日:2017-08-17

    IPC分类号: G06N3/04 G06N3/08

    摘要: Neuromorphic processing apparatus is provided. The present invention may include a spiking neural network comprising a set of input spiking neurons each connected to each of a set of output spiking neurons via a respective synapse for storing a synaptic weight which is adjusted for that synapse in dependence on network operation in a learning mode of the apparatus, and each synapse is operable to provide a post-synaptic signal, dependent on its synaptic weight, to its respective output neuron. The present invention may further include a pre-processor unit adapted to process input data, defining a pattern of data points, to produce a first set of input spike signals which encode values representing respective data points, and a second set of input spike signals which encode values complementary to respective said values representing data points, and to supply the input spike signals to respective predetermined input neurons of the network.

    ARTIFICIAL NEURON APPARATUS
    30.
    发明申请

    公开(公告)号:US20170270404A1

    公开(公告)日:2017-09-21

    申请号:US15075314

    申请日:2016-03-21

    IPC分类号: G06N3/063

    CPC分类号: G06N3/0635 G06N3/049

    摘要: Artificial neuron apparatus includes a resistive memory cell connected in an input circuit having a neuron input, for receiving neuron input signals, and a current source for supplying a read current to the cell. The input circuit is selectively configurable in response to a set of control signals, defining alternating read and write phases of operation, to apply the read current to the cell during the read phase and to apply a programming current to the cell, for programming cell resistance, on receipt of a neuron input signal during the write phase. The cell resistance is progressively changed from a first state to a second state in response to successive neuron input signals. The apparatus further includes an output circuit comprising a neuron output and a digital latch which is connected to the input circuit for receiving a measurement signal dependent on cell resistance.