Microsoft technology licensing, llc (20250005339). MACHINE LEARNING MODEL WITH DEPTH PROCESSING UNITS

MACHINE LEARNING MODEL WITH DEPTH PROCESSING UNITS

Organization Name

microsoft technology licensing, llc

Inventor(s)

Jinyu Li of Redmond WA US

Liang Lu of Redmond WA US

Changliang Liu of Bothell WA US

Yifan Gong of Sammamish WA US

MACHINE LEARNING MODEL WITH DEPTH PROCESSING UNITS

This abstract first appeared for US patent application 20250005339 titled 'MACHINE LEARNING MODEL WITH DEPTH PROCESSING UNITS

Original Abstract Submitted

representative embodiments disclose machine learning classifiers used in scenarios such as speech recognition, image captioning, machine translation, or other sequence-to-sequence embodiments. the machine learning classifiers have a plurality of time layers, each layer having a time processing block and a depth processing block. the time processing block is a recurrent neural network such as a long short term memory (lstm) network. the depth processing blocks can be an lstm network, a gated deep neural network (dnn) or a maxout dnn. the depth processing blocks account for the hidden states of each time layer and uses summarized layer information for final input signal feature classification. an attention layer can also be used between the top depth processing block and the output layer.