公开(公告)号：US12067484B2

公开(公告)日：2024-08-20

申请号：US16449264

申请日：2019-06-21

Applicant: Xilinx, Inc.

Inventor： Yaman Umuroglu ,  Nicholas Fraser ,  Michaela Blott ,  Kristof Denolf ,  Kornelis A. Vissers

IPC: G06N3/063 ,  G06N3/08 ,  G06N3/082 ,  G06N3/084

CPC classification number: G06N3/08 ,  G06N3/063 ,  G06N3/082 ,  G06N3/084

Abstract: An example method of training a neural network includes defining hardware building blocks (HBBs), neuron equivalents (NEQs), and conversion procedures from NEQs to HBBs; defining the neural network using the NEQs in a machine learning framework; training the neural network on a training platform; and converting the neural network as trained into a netlist of HBBs using the conversion procedures to convert the NEQs in the neural network to the HBBs of the netlist.

公开(公告)号：US11615300B1

公开(公告)日：2023-03-28

申请号：US16007884

申请日：2018-06-13

Applicant: Xilinx, Inc.

Inventor： Julian Faraone ,  Michaela Blott ,  Nicholas Fraser

IPC: G06N3/08 ,  G06N3/04

Abstract: A neural network system includes an input layer, one or more hidden layers, and an output layer. A first layer circuit implements a first layer of the one or more hidden layers. The first layer includes a first weight space including one or more subgroups. A forward path circuit of the first layer circuit includes a multiply and accumulate circuit to receive an input from a layer preceding the first layer; and provide a first subgroup weighted sum using the input and a first plurality weights associated with a first subgroup. A scaling coefficient circuit provides a first scaling coefficient associated with the first subgroup, and applies the first scaling coefficient to the first subgroup weighted sum to generate a first subgroup scaled weighted sum. An activation circuit generates an activation based on the first subgroup scaled weighted sum and provide the activation to a layer following the first layer.

公开(公告)号：US11934932B1

公开(公告)日：2024-03-19

申请号：US17094598

申请日：2020-11-10

Applicant: XILINX, INC.

Inventor： Giulio Gambardella ,  Nicholas Fraser ,  Ussama Zahid ,  Michaela Blott ,  Kornelis A. Vissers

IPC: G06N20/20 ,  G06F11/16 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06N20/20 ,  G06F11/16 ,  G06N3/045 ,  G06N3/08

Abstract: Examples herein propose operating redundant ML models which have been trained using a boosting technique that considers hardware faults. The embodiments herein describe performing an evaluation process where the performance of a first ML model is measured in the presence of a hardware fault. The errors introduced by the hardware fault can then be used to train a second ML model. In one embodiment, a second evaluation process is performed where the combined performance of both the first and second trained ML models is measured in the presence of a hardware fault. The resulting errors can then be used when training a third ML model. In this manner, the three trained ML models are trained to be error aware. As a result, during operation, if a hardware fault occurs, the three ML models have better performance relative to three ML models that where not trained to be error aware.

公开(公告)号：US20190080223A1

公开(公告)日：2019-03-14

申请号：US15705033

申请日：2017-09-14

Applicant: Xilinx, Inc.

Inventor： Nicholas Fraser ,  Michaela Blott

IPC: G06N3/04 ,  G06N3/08

Abstract: A neural network system includes an input layer, one or more hidden layers, and an output layer. The input layer receives a training set including a sequence of batches and provides to its following layer output activations associated with the sequence of batches respectively. A first hidden layer receives, from its preceding layer, a first input activation associated with a first batch, receive a first input gradient associated with a second batch preceding the first batch, and provide, to its following layer a first output activation associated with the first batch based on the first input activation and first input gradient. The first and second batches have a delay factor associated with at least two batches. The output layer receives, from its preceding layer, a second input activation, and provide, to its preceding layer, a first output gradient based on the second input activation and the first training set.