Search Results for author:
Found 2 papers, 0 papers with code
Comparative Study: Standalone IEEE 16-bit Floating-Point for Image Classification
Contrary to literature that credits the success of noise-tolerated neural networks to regularization effects, our study-supported by a series of rigorous experiments-provides a quantitative explanation of why standalone IEEE 16-bit floating-point neural networks can perform on par with 32-bit and mixed-precision networks in various image classification tasks.
The Hidden Power of Pure 16-bit Floating-Point Neural Networks
Lowering the precision of neural networks from the prevalent 32-bit precision has long been considered harmful to performance, despite the gain in space and time.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
