公开(公告)号：EP4145242B1

公开(公告)日：2024-07-10

申请号：EP22193345.0

申请日：2022-08-31

IPC分类号： G05D1/00 ,  G06N3/092 ,  B60W60/00

CPC分类号： G05D1/0214 ,  B60W60/00 ,  G06N3/092 ,  G06N3/0464 ,  B60W2720/10620130101 ,  B60W2710/20720130101

公开(公告)号：EP3834138B1

公开(公告)日：2024-06-26

申请号：EP19782529.2

申请日：2019-09-27

IPC分类号： G06N3/084 ,  G06N3/044 ,  G06N3/0464 ,  G06N3/045 ,  G06N3/092 ,  G06F18/20 ,  G06N3/006 ,  G06V10/44 ,  G06V10/778 ,  G06V10/82 ,  G06V10/96 ,  G06V10/70

CPC分类号： G06N3/006 ,  G06N3/084 ,  G06V10/96 ,  G06V10/454 ,  G06V10/82 ,  G06V10/87 ,  G06V10/7788 ,  G06N3/044 ,  G06N3/045 ,  G06F18/285 ,  G06N3/092 ,  G06N3/0464

公开(公告)号：EP4386632A1

公开(公告)日：2024-06-19

申请号：EP22213403.3

申请日：2022-12-14

申请人： Robert Bosch GmbH

发明人： Vinogradska, Julia ,  Peters, Jan ,  Berkenkamp, Felix ,  Bottero, Alessandro Giacomo ,  Luis Goncalves, Carlos Enrique

IPC分类号： G06N3/092 ,  G06N3/045

CPC分类号： G06N3/092 ,  G06N3/045

摘要： According to various embodiments, a method for training a control policy is described, comprising estimating the variance of a value function which associates a state with a value of the state or a pair of state and action with a value of the pair by solving a Bellman uncertainty equation, wherein, for each of multiple states, the reward function of the Bellman uncertainty equation is set to the difference of the total uncertainty about the mean of the value of the subsequent state following the state and the average aleatoric uncertainty of the value of the subsequent state and biasing the control policy in training towards regions for which the estimation gives a higher variance of the value function than for other regions.

公开(公告)号：EP4384953A1

公开(公告)日：2024-06-19

申请号：EP22800200.2

申请日：2022-10-05

申请人： DeepMind Technologies Limited

发明人： GOYAL, Anirudh ,  BANINO, Andrea ,  FRIESEN, Abram Luke ,  WEBER, Theophane Guillaume ,  BADIA, Adrià Puigdomènech ,  KE, Nan ,  OSINDERO, Simon ,  LILLICRAP, Timothy Paul ,  BLUNDELL, Charles

IPC分类号： G06N3/092 ,  G06N3/006 ,  G06N3/042 ,  G06N3/0442 ,  G06N3/0455 ,  G06N3/0464 ,  G06N3/084

CPC分类号： G06N3/006 ,  G06N3/084 ,  G06N3/042 ,  G06N3/0442 ,  G06N3/092 ,  G06N3/0455 ,  G06N3/0464

公开(公告)号：EP3535702B1

公开(公告)日：2024-05-01

申请号：EP17801215.9

申请日：2017-11-06

IPC分类号： G06N3/006 ,  G06N3/045 ,  G06N3/092

CPC分类号： G06N3/006 ,  G06N3/045 ,  G06N3/092

公开(公告)号：EP3586277B1

公开(公告)日：2024-04-03

申请号：EP18710220.7

申请日：2018-02-23

发明人： NACHUM, Ofir ,  NOROUZI, Mohammad ,  SCHUURMANS, Dale Eric ,  XU, Kelvin

IPC分类号： G06N3/092 ,  G06N3/045 ,  G06N3/006 ,  G06N3/0442 ,  G06N3/0464

公开(公告)号：EP3446258B1

公开(公告)日：2024-03-27

申请号：EP17727993.2

申请日：2017-05-18

发明人： BLUNDELL, Charles ,  URIA-MARTINEZ, Benigno

IPC分类号： G06N3/092 ,  G06N3/0455 ,  G06N3/047 ,  G06N20/00 ,  G06N3/006

公开(公告)号：EP4220487A3

公开(公告)日：2024-02-14

申请号：EP23163801.6

申请日：2023-03-23

申请人： Beijing Baidu Netcom Science Technology Co., Ltd.

发明人： ZHANG, Weijia ,  ZHANG, Le ,  LIU, Hao ,  HAN, Jindong ,  QIN, Chuan ,  ZHU, Hengshu ,  XIONG, Hui

IPC分类号： G06N3/045 ,  G06N3/0895 ,  G06N3/092 ,  B60L53/00 ,  G06Q50/06 ,  G06N3/0464 ,  G06N3/084

摘要： A method and apparatus for training an information adjustment model of a charging station, an electronic device, and a storage medium. An implementation comprises: acquiring a battery charging request, and determining environment state information corresponding to each charging station in a charging station set; determining, through an initial policy network, target operational information of the each charging station in the charging station set for the battery charging request, according to the environment state information; determining, through an initial value network, a cumulative reward expectation corresponding to the battery charging request according to the environment state information and the target operational information; training the initial policy network and the initial value network by using a deep deterministic policy gradient algorithm; and determining a trained policy network as an information adjustment model corresponding to the each charging station.

公开(公告)号：EP4300857A1

公开(公告)日：2024-01-03

申请号：EP23181046.6

申请日：2023-06-22

申请人： Nokia Technologies Oy

发明人： KOVÁCS, István Zsolt ,  VEIJALAINEN, Teemu Mikael ,  KELA, Kalle Petteri ,  SONG, Jian ,  BUTT, Muhammad Majid

IPC分类号： H04L1/00 ,  G06N3/006 ,  G06N3/092 ,  G06N3/098 ,  G06N7/01

摘要： There is provided an apparatus for a first communication node, the apparatus comprising: means for synchronising a common reference timing with a second communication node; means for obtaining an indication of a time window, wherein the time window specifies a period of time between a first time instance and a second time instance; and means for configuring a machine learning-based function at the first communication node, wherein the configuration of the machine learning-based function is common between the first and second communication nodes. The apparatus further comprising means for executing the machine learning-based function; and means for obtaining information by measuring a performance metric, for the machine learning-based function, during the time window. The apparatus further comprising means for assigning a time identification to the measured information during the time window, wherein the time identification is associated with the common reference timing; and means for providing, to the second communication node, the measured information according to the time identification.

公开(公告)号：EP4290412A3

公开(公告)日：2024-01-03

申请号：EP23204765.4

申请日：2018-09-05

申请人： Sartorius Stedim Data Analytics AB

发明人： SJÖGREN, Rickard ,  TRYGG, Johan

IPC分类号： G06N3/04 ,  G05B23/02 ,  G06N3/0442 ,  G06N3/0455 ,  G06N3/0464 ,  G06N3/048 ,  G06N3/092 ,  G06N3/088

摘要： A computer-implemented method for data analysis is provided. The method comprises: obtaining a deep neural network (100) for processing data and at least a part of a training dataset used for training the deep neural network, the deep neural network comprising a plurality of hidden layers, the training dataset including possible observations that can be input to the deep neural network, the deep neural network being trained using the training dataset; obtaining first sets of intermediate output values that are output from at least one of the plurality of hidden layers, each of the first sets of intermediate output values obtained by inputting a different one of the possible observations included in said at least the part of the training dataset; constructing a latent variable model using the first sets of intermediate output values, the latent variable model providing a mapping of the first sets of intermediate output values to first sets of latent variables for the latent variable model in a sub-space that has a dimension lower than a dimension of the sets of the intermediate outputs; and storing the latent variable model and the first sets of latent variables for the latent variable model in a storage medium.