- Patent Title: Quantizing trained neural networks with removal of normalization
-
Application No.: US16727629Application Date: 2019-12-26
-
Publication No.: US11861492B1Publication Date: 2024-01-02
- Inventor: Ming Kai Hsu
- Applicant: Cadence Design Systems, Inc.
- Applicant Address: US CA San Jose
- Assignee: Cadence Design Systems, Inc.
- Current Assignee: Cadence Design Systems, Inc.
- Current Assignee Address: US CA San Jose
- Agency: Schwegman Lundberg & Woessner, P.A.
- Main IPC: G10L15/00
- IPC: G10L15/00 ; G06N3/08 ; G06N3/04
Abstract:
Various embodiments provide for quantizing a trained neural network with removal of normalization with respect to at least one layer of the quantized neural network, such as a quantized multiple fan-in layer (e.g., element-wise add or sum layer).
Information query
