In this talk we present Block Minifloat (BM) arithmetic, a parameterised minifloat format which is optimised for low-precision deep learning applications. While standard floating-point representations have two degrees of freedom, the exponent and mantissa, BM exposes an additional exponent bias allowing the range of a block to be controlled. Results for inference, training and transfer learning using 4-8 bit precision which achieve similar accuracy to floating point will be presented.
Schedule
Timezone: PDT
Low Precision Inference and Training for Deep Neural Networks
Philip LEONG, Professor
University of Sydney
Philip LEONG, Professor
University of Sydney
In this talk we present Block Minifloat (BM) arithmetic, a parameterised minifloat format which is optimised for low-precision deep learning applications. While standard floating-point representations have two degrees of freedom, the exponent and mantissa, BM exposes an additional exponent bias allowing the range of a block to be controlled. Results for inference, training and transfer learning using 4-8 bit precision which achieve similar accuracy to floating point will be presented.
Schedule subject to change without notice.