Google Inc.

Synopsys, Inc.

Jay K Adams

Manas Rajendra Joglekar

Quoc V Le

Pranav Khaitan

Cong Li

Mei Chen

Sujeet Bansal

Qingzhou Wang

Yong Xiao

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.

Learning to select vocabularies for categorical features

The present disclosure is directed to systems and methods that include a machine-learned label embedding model that generates feature-based label embeddings for labels in real-time, in furtherance, for example, of selection of labels relative to a particular entity. In particular, one example computing system includes both a machine-learned entity embedding model configured to receive and process entity feature data descriptive of an entity to generate an entity embedding for the entity and a machine-learned label embedding model configured to receive and process first label feature data associated with a first label to generate a first label embedding for the first label.

Real-time on the fly generation of feature-based label embeddings via machine learning

One embodiment of the present invention provides a system that optimizes a circuit design during a logic design stage to reduce routing congestion during a placement and routing stage. During operation, this system identifies a first circuit structure in the circuit design which is expected to cause routing congestion during the placement and routing stage. Next, the system generates a second circuit structure which is functionally equivalent to the first circuit structure, and is not expected to cause routing congestion during the placement and routing stage. The system then replaces the first circuit structure in the circuit design with the second circuit structure, thereby mitigating routing congestion during the placement and routing stage.

Congestion optimization during synthesis

Growing community of inventors

San Carlos, CA, United States of America

Jay K Adams