Alert button
Picture for Ganesh Dasika

Ganesh Dasika

Alert button

Rank and run-time aware compression of NLP Applications

Oct 06, 2020
Urmish Thakker, Jesse Beu, Dibakar Gope, Ganesh Dasika, Matthew Mattina

Figure 1 for Rank and run-time aware compression of NLP Applications
Figure 2 for Rank and run-time aware compression of NLP Applications
Figure 3 for Rank and run-time aware compression of NLP Applications
Viaarxiv icon

Pushing the limits of RNN Compression

Oct 09, 2019
Urmish Thakker, Igor Fedorov, Jesse Beu, Dibakar Gope, Chu Zhou, Ganesh Dasika, Matthew Mattina

Figure 1 for Pushing the limits of RNN Compression
Viaarxiv icon

Compressing RNNs for IoT devices by 15-38x using Kronecker Products

Jun 18, 2019
Urmish Thakker, Jesse Beu, Dibakar Gope, Chu Zhou, Igor Fedorov, Ganesh Dasika, Matthew Mattina

Figure 1 for Compressing RNNs for IoT devices by 15-38x using Kronecker Products
Figure 2 for Compressing RNNs for IoT devices by 15-38x using Kronecker Products
Figure 3 for Compressing RNNs for IoT devices by 15-38x using Kronecker Products
Figure 4 for Compressing RNNs for IoT devices by 15-38x using Kronecker Products
Viaarxiv icon

Run-Time Efficient RNN Compression for Inference on Edge Devices

Jun 18, 2019
Urmish Thakker, Jesse Beu, Dibakar Gope, Ganesh Dasika, Matthew Mattina

Figure 1 for Run-Time Efficient RNN Compression for Inference on Edge Devices
Figure 2 for Run-Time Efficient RNN Compression for Inference on Edge Devices
Figure 3 for Run-Time Efficient RNN Compression for Inference on Edge Devices
Figure 4 for Run-Time Efficient RNN Compression for Inference on Edge Devices
Viaarxiv icon

Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications

Mar 04, 2019
Dibakar Gope, Ganesh Dasika, Matthew Mattina

Figure 1 for Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications
Figure 2 for Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications
Figure 3 for Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications
Figure 4 for Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications
Viaarxiv icon

Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs

Mar 04, 2019
Partha Maji, Andrew Mundy, Ganesh Dasika, Jesse Beu, Matthew Mattina, Robert Mullins

Figure 1 for Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs
Figure 2 for Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs
Figure 3 for Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs
Figure 4 for Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs
Viaarxiv icon