research
∙
08/25/2023
Linear Oscillation: The Aesthetics of Confusion for Vision Transformer
Activation functions are the linchpins of deep learning, profoundly infl...
share
research
∙
07/30/2023
An Efficient Approach to Mitigate Numerical Instability in Backpropagation for 16-bit Neural Network Training
In this research, we delve into the intricacies of the numerical instabi...
research
∙
06/20/2023
G-NM: A Group of Numerical Time Series Prediction Models
In this study, we focus on the development and implementation of a compr...
research
∙
05/18/2023
Comparative Study: Standalone IEEE 16-bit Floating-Point for Image Classification
Reducing the number of bits needed to encode the weights and activations...
research
∙
01/30/2023
The Hidden Power of Pure 16-bit Floating-Point Neural Networks
Lowering the precision of neural networks from the prevalent 32-bit prec...
research
∙
01/17/2023