US 12,079,981 B2
Hybrid deep learning for anomaly detection
Vinay Sawal, Fremont, CA (US); Per Henrik Fremrot, Novato, CA (US); and Sithiqu Shahul Hameed, Chennai (IN)
Assigned to DELL PRODUCTS L.P., Round Rock, TX (US)
Filed by DELL PRODUCTS L.P., Round Rock, TX (US)
Filed on Jun. 29, 2021, as Appl. No. 17/362,970.
Claims priority of application No. 202111024969 (IN), filed on Jun. 4, 2021.
Prior Publication US 2022/0392056 A1, Dec. 8, 2022
Int. Cl. G06T 7/00 (2017.01); G06F 16/901 (2019.01)
CPC G06T 7/0008 (2013.01) [G06F 16/9024 (2019.01); G06T 2207/10081 (2013.01); G06T 2207/10116 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for detecting an anomaly, the method comprising:
receiving, at a Graph Attention Network (GAT), data associated with objects, the GAT
threating each of the objects as a node, treating connections between objects as edges in a graph, and performing a graph-based convolution using multi-head attention;
obtaining from the GAT a first output set of hidden representations;
receiving, at a Convolutional Neural Network (CNN), at least some of the data;
obtaining from the CNN a second output set of hidden representations;
concatenating the first and second output sets of hidden representations to obtain a concatenated set of representations; and
detecting whether an anomaly exists using the concatenated set of representations and a third neural network, which receives the concatenated set of representations as an input.