We propose a Quantization Guided Training (QGT) method to guide DNN training towards optimized low-bit-precision targets and reach extreme compression levels below 8-bit precision.
Quantization for deep neural networks (DNN) have enabled developers to deploy models with less memory and more efficient low-power inference.
Conditional computation for Deep Neural Networks (DNNs) reduce overall computational load and improve model accuracy by running a subset of the network.
Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference.
Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience.
The use of deep neural networks in edge computing devices hinges on the balance between accuracy and complexity of computations.
Specifically, we first train a temporal deep learning model, using only normal HPC readings from legitimate processes that run daily in these power-grid systems, to model the normal behavior of the power-grid controller.
Our key idea is to control the expressive power of the network by dynamically quantizing the range and set of values that the parameters can take.