-
1.发明公开公开(公告)号：US20240330787A1
公开(公告)日：2024-10-03
申请号：US18493639
申请日：2023-10-24
摘要： State of the art approaches for training chained neural network models for delay prediction train the data models using only real data and not predicted data. Such models when used in a chained way leads to worse results as they are not exposed to predicted data during training. This leads to the model prediction errors showing sharp increase as the models tries to predict for subsequent stations past the immediate station. Embodiments disclosed herein provide a method and system for training of chained neural networks for delay prediction in transit networks. In this approach, a chained neural network model used by the system is trained such that data containing a mix of real data and predicted data is used for training each data model in a sequence of data models in the chained neural network model.
-
2.发明公开公开(公告)号：US20230289574A1
公开(公告)日：2023-09-14
申请号：US17815222
申请日：2022-07-27
IPC分类号： G06N3/04
CPC分类号： G06N3/0481
摘要： An Extended Kalman filter (EKF) is a general nonlinear version of the Kalman filter and an approximate inference solution which uses a linearized approximation performed dynamically at each step and followed by linear KF application. Extended Kalman Filter involves dynamic computation of the partial derivatives of the non-linear functions system maps with respect to the input or current state. Existing approaches have failed to perform recursive computations efficiently and exactly for such scenarios. Embodiments of the present disclosure efficient forward and backward recursion-based approaches wherein a forward pass is executed through a feed-forward network (FFN) to compute a value that serves as an input to jth node at a layer l from a plurality of network layers of the FFN and partial derivatives are estimated for each node associated with various network layers in the FFN. The feed-forward network is used as state and/or observation equation in the EKF.
-
搜索结果
2 条记录 (耗时 0.014 秒)
