Search Results for author: Karina Vasquez

Found 1 papers, 0 papers with code

Activation Density based Mixed-Precision Quantization for Energy Efficient Neural Networks

no code implementations12 Jan 2021 Karina Vasquez, Yeshwanth Venkatesha, Abhiroop Bhattacharjee, Abhishek Moitra, Priyadarshini Panda

Additionally, we find that integrating AD based quantization with AD based pruning (both conducted during training) yields up to ~198x and ~44x energy reductions for VGG19 and ResNet18 architectures respectively on PIM platform compared to baseline 16-bit precision, unpruned models.

Model Compression Quantization

Cannot find the paper you are looking for? You can Submit a new open access paper.