公开(公告)号：US12118286B2

公开(公告)日：2024-10-15

申请号：US17438551

申请日：2020-03-09

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Yusuke Koumura

IPC: G06F30/392 ,  G06N3/04 ,  G06N3/08 ,  G06N20/00

CPC classification number: G06F30/392 ,  G06N3/04 ,  G06N3/08 ,  G06N20/00

Abstract: A novel wiring layout design method is provided. A wiring layout in which a starting terminal group and an end terminal group are electrically connected to each other is generated using layout information and a netlist. In the case where the wiring layout satisfies a design rule, a wiring resistance and a parasitic capacitance of the wiring layout are extracted. The layout information is updated using Q learning and a new wiring layout is generated. In the Q learning, a positive reward is given when the values of the wiring resistance and the parasitic capacitance decrease, and a weight of the neural network is updated in accordance with the reward. In the case where the new wiring layout satisfies the design rule, a wiring resistance and a parasitic capacitance of the new wiring layout are extracted. In the case where the change rate of the wiring resistance and the parasitic capacitance is high, the layout information is updated using the Q learning.

公开(公告)号：US10949595B2

公开(公告)日：2021-03-16

申请号：US16622054

申请日：2018-06-14

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Naoaki Tsutsui ,  Yusuke Koumura ,  Yuji Iwaki ,  Shunpei Yamazaki

IPC: G06F30/392 ,  G06N3/08 ,  G06N3/04 ,  G06F30/27

Abstract: A system performs a layout design of a circuit for a small area satisfying a design rule within a short period of time. In a layout design system which includes a processing portion and in which a circuit diagram and layout design information are input to the processing portion, the processing portion has a function of generating layout data from the circuit diagram and the layout design information by performing a Q learning, the processing portion has a function of outputting the layout data, the processing portion includes a first neural network, and the first neural network estimates an action value function in the Q learning.

公开(公告)号：US12217767B2

公开(公告)日：2025-02-04

申请号：US17630090

申请日：2020-07-29

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Fumiya Nagashima ,  Kengo Akimoto ,  Tatsuya Okano ,  Yusuke Koumura ,  Seiko Inoue

IPC: G10L21/0272 ,  G10L25/30

Abstract: An audio device capable of inhibiting malfunction of an information terminal is provided. The audio device includes a sound sensor portion, a sound separation portion, a sound determination portion, and a processing portion. The sound sensor portion has a function of sensing sound. The sound separation portion has a function of separating the sound sensed by the sound sensor portion into a voice and sound other than a voice. The sound determination portion has a function of storing the feature quantity of the sound. The sound determination portion has a function of determining, with a machine learning model such as a neural network model, whether the feature quantity of the voice separated by the sound separation portion is the stored feature quantity. The processing portion has a function of analyzing an instruction contained in the voice and generating an instruction signal representing the content of the instruction in the case where the feature quantity of the voice is the stored feature quantity. The processing portion has a function of performing, on the sound other than a voice separated by the sound separation portion, processing for canceling the sound other than a voice. Specifically, the processing portion has a function of performing, on the sound other than a voice, processing for inverting the phase thereof.