13 citations · 16 across the 4 of their papers we have counts for
10 papers
Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices
Urmish Thakker, Paul N. Whatmough, Zhigang Liu +2
Structured matrices, such as those derived from Kronecker products (KP), are effective at compressing neural networks, but can lead to unacceptable accuracy loss when applied to la…
Rank and run-time aware compression of NLP Applications
Urmish Thakker, Jesse Beu, Dibakar Gope +2
Sequence model based NLP applications can be large. Yet, many applications that benefit from them run on small devices with very limited compute and storage capabilities, while sti…
High Throughput Matrix-Matrix Multiplication between Asymmetric Bit-Width Operands
Dibakar Gope, Jesse Beu, Matthew Mattina
Matrix multiplications between asymmetric bit-width operands, especially between 8- and 4-bit operands are likely to become a fundamental kernel of many important workloads includi…
Compressing Language Models using Doped Kronecker Products
Urmish Thakker, Paul N. Whatmough, Zhi-Gang Liu +2
Kronecker Products (KP) have been used to compress IoT RNN Applications by 15-38x compression factors, achieving better results than traditional compression methods. However when K…
Ternary MobileNets via Per-Layer Hybrid Filter Banks
Dibakar Gope, Jesse Beu, Urmish Thakker +1
MobileNets family of computer vision neural networks have fueled tremendous progress in the design and organization of resource-efficient architectures in recent years. New applica…
Pushing the limits of RNN Compression
Urmish Thakker, Igor Fedorov, Jesse Beu +4
Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can signi…