BIT WIDTH SELECTION FOR FIXED POINT NEURAL NETWORKS

• Main Authors: JULIAN, David Jonathan, WIERZYNSKI, Casimir Matthew, ANNAPUREDDY, Venkata Sreekanta Reddy, LIN, Dexu
• Format: Patent
• Language: English; French; German
• Published: 10.03.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

A method for selecting bit widths for a fixed point machine learning model includes evaluating a sensitivity of model accuracy to bit widths at each computational stage of the model. The method also includes selecting a bit width for parameters, and/or intermediate calculations in the computational...