Compact Neural Representation Using Attentive Network Pruning | AISC
Speaker(s): Mahdi Biparva
Find the recording, slides, and more info at https://ai.science/e/compact-neural-representation-using-attentive-network-pruning--MXNTz9Odz6Lqn1NGCqmC
Motivation / Abstract
Pruning becomes increasingly popular as we seek to migrate deep learning to smaller mobile platforms. The paper demonstrates a pruning technique that not only outperforms baseline models, but also proves a high compression ratio is achievable with negligible loss of accuracy. It is able to achieve such results by introducing a novel hierarchical selection mechanism as the basis of pruning.
What was discussed?
- Neural Network Compression
- Topdown selection
- Pruning mechanisms
------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit https://ai.science for more details