Invention Publication
- Patent Title: LOOK-UP TABLE BASED NEURAL NETWORKS
-
Application No.: US17978026Application Date: 2022-10-31
-
Publication No.: US20230186082A1Publication Date: 2023-06-15
- Inventor: Michele Covell , David Marwood , Shumeet Baluja , Nicholas Johnston
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06F1/03 ; G06N3/048

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing a network input using a neural network to generate a network output for the network input. One of the methods includes maintaining, for each of the plurality of neural network layers, a respective look-up table that maps each possible combination of a quantized input index and a quantized weight index to a multiplication result; and generating a network output from a network input, comprising, for each of the neural network layers: receiving data specifying a quantized input to the neural network layer, the quantized input comprising a plurality of quantized input values; and generating a layer output for the neural network layer from the quantized input to the neural network layer using the respective look-up table for the neural network layer.
Public/Granted literature
- US12118466B2 Look-up table based neural networks Public/Granted day:2024-10-15
Information query