公开(公告)号：WO2017136104A1

公开(公告)日：2017-08-10

申请号：PCT/US2017/012730

申请日：2017-01-09

Applicant: QUALCOMM INCORPORATED

Inventor： O'CONNOR, Peter ,  WELLING, Max

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/049 ,  G06N3/084

Abstract: A method of training a neural network with back propagation includes generating error events representing a gradient of a cost function for the neural network. The error events may be generated based on a forward pass through the neural network resulting from input events, weights of the neural network and events from a target signal. The method further includes updating the weights of the neural network based on the error events.

Abstract translation: 用反向传播训练神经网络的方法包括产生表示神经网络的代价函数的梯度的误差事件。 可以基于由输入事件，神经网络的权重和来自目标信号的事件引起的神经网络的正向通过来生成错误事件。 该方法还包括基于错误事件更新神经网络的权重。

公开(公告)号：WO2018212946A1

公开(公告)日：2018-11-22

申请号：PCT/US2018/029180

申请日：2018-04-24

Applicant: QUALCOMM INCORPORATED

Inventor： O'CONNOR, Peter ,  WELLING, Max

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

CPC classification number: G06N3/084 ,  G06N3/04 ,  G06N3/049 ,  G06N3/063

Abstract: A method for processing temporally redundant data in an artificial neural network (ANN) includes encoding an input signal, received at an initial layer of the ANN, into an encoded signal. The encoded signal comprises the input signal and a rate of change of the input signal. The method also includes quantizing the encoded signal into integer values and computing an activation signal of a neuron in a next layer of the ANN based on the quantized encoded signal. The method further includes computing an activation signal of a neuron at each layer subsequent to the next layer to compute a full forward pass of the ANN. The method also includes back propagating approximated gradients and updating parameters of the ANN based on an approximate derivative of a loss with respect to the activation signal.

公开(公告)号：WO2018084941A1

公开(公告)日：2018-05-11

申请号：PCT/US2017/052083

申请日：2017-09-18

Applicant: QUALCOMM INCORPORATED

Inventor： O'CONNOR, Peter ,  WELLING, Max

IPC: G06N3/04

CPC classification number: G06N3/049

Abstract: A method of computation in a deep neural network includes discretizing input signals and computing a temporal difference of the discrete input signals to produce a discretized temporal difference. The method also includes applying weights of a first layer of the deep neural network to the discretized temporal difference to create an output of a weight matrix. The output of the weight matrix is temporally summed with a previous output of the weight matrix. An activation function is applied to the temporally summed output to create a next input signal to a next layer of the deep neural network.

Abstract translation: 在深度神经网络中的计算方法包括离散输入信号并计算离散输入信号的时间差以产生离散时间差。 该方法还包括将深度神经网络的第一层的权重应用于离散时间差以创建权重矩阵的输出。 权重矩阵的输出在时间上与权重矩阵的先前输出相加。 将激活函数应用于时间求和输出以创建下一个输入信号到深层神经网络的下一层。