公开(公告)号：US20180253401A1

公开(公告)日：2018-09-06

申请号：US15903290

申请日：2018-02-23

Applicant: SONY CORPORATION

Inventor： Fabien CARDINAUX ,  Stefan UHLICH ,  Thomas KEMP ,  Javier ALONSO GARCIA ,  Kazuki YOSHIYAMA

IPC: G06F17/16 ,  G06N3/08

CPC classification number: G06F17/16 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/08

Abstract: An apparatus comprising circuitry that implements an artificial neural network training algorithm that uses weight tying.

公开(公告)号：US20210042453A1

公开(公告)日：2021-02-11

申请号：US16981289

申请日：2018-12-27

Applicant: Sony Corporation ,  Sony Semiconductor Solutions Corporation

Inventor： Kazuki YOSHIYAMA ,  Takumi YAJIMA ,  Ryoji IKEGAYA

IPC: G06F30/20 ,  G06N3/04

Abstract: [Problem] To provide design support useful for hardware implementation of a neural network.
[Solution] Provided is an information processing device including a control unit that controls presentation of information related to an optimization structure when at least a part of a network structure of a designed neural network has been optimized for hardware processing. Provided is an information processing method including a step of controlling, by a processor, presentation of information related to an optimization structure when at least a part of a network structure of a designed neural network has been optimized for hardware processing.

公开(公告)号：US20200257506A1

公开(公告)日：2020-08-13

申请号：US15774318

申请日：2016-11-25

Applicant: SONY CORPORATION

Inventor： Kazuki YOSHIYAMA ,  Yoshiyuki KOBAYASHI

IPC: G06F8/34 ,  G06F17/18 ,  G06F3/0482 ,  G06F3/0484 ,  G06N3/063

Abstract: There is provided an information processing apparatus and an information processing method to present information for improving development efficiency of a neural network to a user. The information processing method includes: providing, by a processor, a form for creating a program for establishing a neural network on a basis of a disposed component and property set for the component; and presenting statistical information relating to the neural network. The information processing apparatus includes a form control unit configured to provide a form for creating a program for establishing a neural network on a basis of a disposed component and property set for the component. The form control unit presents statistical information relating to the neural network.

公开(公告)号：US20200380356A1

公开(公告)日：2020-12-03

申请号：US16463974

申请日：2018-02-09

Applicant: SONY CORPORATION

Inventor： Kazuki YOSHIYAMA

IPC: G06N3/08 ,  G06N20/00 ,  G06F17/18

Abstract: There is provided an information processing apparatus, an information processing method, and a program for enabling quantization with high accuracy. Quantization is performed assuming that a distribution of values calculated by a machine learning operation is based on a predetermined probability distribution. The operation is an operation in deep learning, and the quantization is performed on the basis of a notion that a distribution of gradients calculated by the operation based on the deep learning is based on the predetermined probability distribution. The quantization is performed when a value obtained by learning in one apparatus is supplied to another apparatus in distributed learning in which machine learning is performed by a plurality of apparatuses in a distributed manner. The present technology can be applied to an apparatus that performs machine learning such as deep learning in a distributed manner.

公开(公告)号：US20180330237A1

公开(公告)日：2018-11-15

申请号：US15774850

申请日：2016-11-25

Applicant: SONY CORPORATION

Inventor： Kazuki YOSHIYAMA ,  Yoshiyuki KOBAYASHI

IPC: G06N3/08 ,  G06F17/30

Abstract: There is provided an information processing apparatus and an information processing method to present information for improving development efficiency of a neural network to a user. The information processing method includes: comparing, by a processor, learning results by a plurality of models of neural networks and presenting comparison information relating to the learning results using a graph. In addition, an information processing apparatus includes a control unit configured to acquire learning results by a plurality of models of neural networks and control comparison information relating to the learning results. The control unit presents the comparison information using a graph. In addition, an information processing apparatus includes a comparing unit configured to compare learning results by a plurality of models of neural networks and generate comparison information relating to the learning results. The comparison information is comparison information using a graph.