DYNAMIC ADAPTATION OF DEEP NEURAL NETWORKS

Techniques are disclosed for training a deep neural network (DNN) for reduced computational resource requirements. A computing system includes a memory for storing a set of weights of the DNN. The DNN includes a plurality of layers. For each layer of the plurality of layers, the set of weights inclu...

Full description

Saved in:
Bibliographic Details
Main Authors Nadamuni Raghavan, Aswin, Chai, Sek Meng, Parajuli, Samyak
Format Patent
LanguageEnglish
Published 30.04.2020
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Techniques are disclosed for training a deep neural network (DNN) for reduced computational resource requirements. A computing system includes a memory for storing a set of weights of the DNN. The DNN includes a plurality of layers. For each layer of the plurality of layers, the set of weights includes weights of the layer and a set of bit precision values includes a bit precision value of the layer. The weights of the layer are represented in the memory using values having bit precisions equal to the bit precision value of the layer. The weights of the layer are associated with inputs to neurons of the layer. Additionally, the computing system includes processing circuitry for executing a machine learning system configured to train the DNN. Training the DNN comprises optimizing the set of weights and the set of bit precision values.
Bibliography:Application Number: US201816133446