Encoder-decoder architectures
EP4747809A1Pending Publication Date: 2026-05-27FEATURESPACE LTD
0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- FEATURESPACE LTD
- Filing Date
- 2023-07-18
- Publication Date
- 2026-05-27
AI Technical Summary
Technical Problem
Existing systems with encoder-decoder architectures face limitations such as restricted downstream utility, lack of data richness, long development and deployment times, overfitting, and high latency.
Method used
The method involves obtaining event data, encoding it using an encoder network, decoding it using a decoder network, and generating loss data to configure the encoder parameters, thereby improving the system's efficiency and effectiveness.
Benefits of technology
This approach enables the generation of transferrable machine learning features, reduces development time, and improves the predictive capacity of downstream models by leveraging rich, automated feature definitions.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure IB2023057328_23012025_PF_FP_ABST
Abstract
Encoder-Decoder Architecture System Control Event data (1024) representing a given event that occurred at a given time is obtained. The event data (1024) is provided as input to an encoder network (1006) to generate encoded event data (1026) comprising an encoded representation of the given event. The encoded event data (1026) is provided as input to a decoder network (1010) to generate decoded event data (1028). The decoded event data (1028) represents one or more further events. Each of the one or more further events occurs at a respective further time. The decoded event data (1028) and reference event data (1030) are provided as inputs to a loss function (1032) to generate loss data. The reference event data (1030) represents the one or more further events. The loss data represents one or more losses of the decoded event data (1028) relative to the reference event data (1030). Encoder configuration data (1032), comprising one or more encoder parameters, is generated using the loss data.
Need to check novelty before this filing date? Find Prior Art