公开(公告)号：US20200302266A1

公开(公告)日：2020-09-24

申请号：US16810582

申请日：2020-03-05

Applicant: STMicroelectronics (Rousset) SAS

Inventor： Pierre Demaj ,  Laurent Folliot

IPC: G06N3/04

Abstract: In accordance with an embodiment, a method includes reducing a size of at least one initial parameter of each layer of an initial multilayer neural network to obtain for each layer a set of new parameters defining a new neural network, wherein each new parameter of the set of new parameters has its data represented in two portions comprising an integer portion and a fractional portion; implementing the new neural network using a test input data set applied only once to each layer; determining a distribution function or a density function resulting from the set of new parameters for each layer; and based on the determined distribution function or density function, adjusting a size of a memory area allocated to the fractional portion and a size of the memory area allocated to the integer portion of each new parameter associated with each layer.

公开(公告)号：US20200183834A1

公开(公告)日：2020-06-11

申请号：US16691957

申请日：2019-11-22

Applicant: STMicroelectronics (Rousset) SAS

Inventor： Laurent Folliot ,  Pierre Demaj

IPC: G06F12/06 ,  G06N3/04

Abstract: A method can be used to determine an overall memory size of a global memory area to be allocated in a memory intended to store input data and output data from each layer of a neural network. An elementary memory size of an elementary memory area intended to store the input data and the output data from the layer is determined for each layer. The elementary memory size is in the range between a memory size for the input data or output data from the layer and a size equal to the sum of the memory size for the input data and the memory size for the output data from the layer. The overall memory size is determined based on the elementary memory sizes associated with the layers. The global memory area contains all the elementary memory areas.

公开(公告)号：US20230131838A1

公开(公告)日：2023-04-27

申请号：US17968148

申请日：2022-10-18

Applicant: STMicroelectronics (Rousset) SAS

Inventor： Pierre Demaj ,  Laurent Folliot

IPC: G06V10/62 ,  G06V10/44 ,  G06K9/00

Abstract: According to one aspect, the disclosure proposes a method for detecting events or features in physical signals by implementing an artificial neural network. The method includes evaluating the probability of presence of the event or feature by implementing the artificial neural network. The method includes implementing the artificial neural network in a nominal mode and to which a physical signal having a first so-called nominal resolution is fed, as long as the probability of the presence of the event or feature is below a threshold. The method further includes implementing the artificial neural network in a reduced consumption mode with a reduced resolution, as long as the probability of the presence of the event or feature is above the threshold. The reduced resolution is lower than the first resolution.

公开(公告)号：US20230126848A1

公开(公告)日：2023-04-27

申请号：US17968174

申请日：2022-10-18

Applicant: STMicroelectronics (Rousset) SAS

Inventor： Pierre Demaj ,  Laurent Folliot

IPC: G06N3/04

Abstract: According to one aspect, a method is provided for detecting events or elements in physical signals, including at least one implementation of a reference artificial neural network, at least one implementation of an auxiliary artificial neural network distinct from the reference artificial neural network. The auxiliary artificial neural network being simplified relative to the reference artificial neural network. At least one assessment of a probability of presence of the event or the element by the implementation of the reference artificial neural network or by the implementation of the auxiliary artificial neural network, where the reference artificial neural network is implemented when the probability of presence of the event or the element is greater than a threshold, and wherein the auxiliary artificial neural network is implemented when the probability of presence of the event or the element is below the threshold.

公开(公告)号：US20220188610A1

公开(公告)日：2022-06-16

申请号：US17455770

申请日：2021-11-19

Applicant: STMicroelectronics S.r.I. ,  STMicroelectronics (Rousset) SAS

Inventor： Laurent Folliot ,  Mirko Falchetto ,  Pierre Demaj

IPC: G06N3/063 ,  G06N3/04 ,  G06F12/02

Abstract: According to an aspect, a method is proposed for defining placements, in a volatile memory, of temporary scratch buffers used during an execution of an artificial neural network, the method comprising: determining an execution order of layers of the neural network, defining placements, in a heap memory zone of the volatile memory, of intermediate result buffers generated by each layer, according to the execution order of the layers, determining at least one free area of the heap memory zone over the execution of the layers, defining placements of temporary scratch buffers in the at least one free area of the heap memory zone according to the execution order of the layers.

公开(公告)号：US10929724B2

公开(公告)日：2021-02-23

申请号：US15924608

申请日：2018-03-19

Applicant: STMicroelectronics (Rousset) SAS

Inventor： Pierre Demaj ,  Laurent Folliot

IPC: G06K9/62 ,  G06K9/00

Abstract: A method is provided for monitoring scene detection by an apparatus detecting scenes from among a set of possible reference scenes. It includes an assignment of an identifier to each reference scene, detection of scenes from among the set of possible reference scenes at successive instants of detection with the aid of at least one classification algorithm, and a sliding time filtering processing of these detected current scenes over a filtering window of size M, based on the identifier of each new detected current scene taken into account in the window and a confidence probability associated with this new detected current scene, the output of the filtering processing successively delivering filtered detected scenes.

公开(公告)号：US20200175373A1

公开(公告)日：2020-06-04

申请号：US16680840

申请日：2019-11-12

Applicant: STMicroelectronics (Rousset) SAS

Inventor： Pierre Demaj ,  Laurent Folliot

IPC: G06N3/08 ,  G06N3/04

Abstract: A method can be used with a neural network being implemented by a system having a computation unit coupled to a collection of memories. The method includes analyzing a set of initial parameters defining an initial multilayer neural network. The analyzing includes attempting to reduce an initial memory size of an initial parameter so as to obtain a set of modified parameters defining a modified neural network with respect to the initial network.

公开(公告)号：US10560564B2

公开(公告)日：2020-02-11

申请号：US15799152

申请日：2017-10-31

Applicant: STMicroelectronics (Rousset) SAS

Inventor： Pierre Demaj ,  Laurent Folliot

IPC: H04M1/725 ,  G01D21/02 ,  H04W4/02 ,  H04W12/00 ,  H04W4/029 ,  H04W52/02 ,  H04W4/38 ,  H04W56/00 ,  H04W4/33 ,  H04W4/23

Abstract: A method can be used for managing a real-time detection related to a scene. A succession of steps of scene detection is spaced apart by time intervals. A time interval separating a current step of scene detection from a previous step of scene detection is adjusted according to an adjustment criterion linked to a previous scene actually detected. The succession of steps and the adjustment are performed by a wireless communication apparatus.

公开(公告)号：US20240119309A1

公开(公告)日：2024-04-11

申请号：US18470798

申请日：2023-09-20

Applicant: STMicroelectronics S.r.l. ,  STMicroelectronics (Rousset) SAS

Inventor： Laurent Folliot ,  Marco Lattuada ,  Pierre Demaj

IPC: G06N3/10 ,  G06F8/35 ,  G06F8/41

CPC classification number: G06N3/10 ,  G06F8/35 ,  G06F8/4434

Abstract: In an embodiments a method includes obtaining a neural network (INN), the neural network having a plurality of neural layers, each layer being capable of being executed according to different implementation solutions and impacting a required memory allocation for the execution of the neural network and/or an execution time of the neural network, defining a maximum execution time threshold of the neural network and/or a maximum required memory allocation threshold for the execution of the neural network, determining an optimal required memory allocation size for the execution of the neural network from possible implementation solutions for each layer of the neural network, determining an optimal execution time of the neural network from the possible implementation solutions for each layer of the neural network and estimating a performance loss or a performance gain in terms of execution time and required memory allocation for each implementation solution of each layer of the neural network.

公开(公告)号：US11645519B2

公开(公告)日：2023-05-09

申请号：US16691914

申请日：2019-11-22

Applicant: STMicroelectronics (Rousset) SAS

Inventor： Pierre Demaj ,  Laurent Folliot

IPC: G06N3/04 ,  G06N3/08 ,  G06N20/00 ,  G06F17/16 ,  G06N3/02 ,  G06N3/063 ,  G06N3/045 ,  G06N3/0464

CPC classification number: G06N3/08 ,  G06F17/16 ,  G06N3/02 ,  G06N3/045 ,  G06N3/0464 ,  G06N3/063 ,  G06N20/00

Abstract: A method can be used to process an initial set of data through a convolutional neural network that includes a convolution layer followed by a pooling layer. The initial set is stored in an initial memory along first and second orthogonal directions. The method includes performing a first filtering of the initial set of data by the convolution layer using a first sliding window along the first direction. Each slide of the first window produces a first set of data. The method also includes performing a second filtering of the first sets of data by the pooling layer using a second sliding window along the second direction.