Picture for Forrest N. Iandola

Forrest N. Iandola

Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition

Add code
Sep 21, 2023
Figure 1 for Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Figure 2 for Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Figure 3 for Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Figure 4 for Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Viaarxiv icon

SqueezeBERT: What can computer vision teach NLP about efficient neural networks?

Add code
Jun 19, 2020
Figure 1 for SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Figure 2 for SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Figure 3 for SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Figure 4 for SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Viaarxiv icon

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

Add code
Nov 04, 2016
Figure 1 for SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Figure 2 for SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Figure 3 for SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Figure 4 for SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Viaarxiv icon

Shallow Networks for High-Accuracy Road Object-Detection

Add code
Jun 05, 2016
Figure 1 for Shallow Networks for High-Accuracy Road Object-Detection
Figure 2 for Shallow Networks for High-Accuracy Road Object-Detection
Figure 3 for Shallow Networks for High-Accuracy Road Object-Detection
Figure 4 for Shallow Networks for High-Accuracy Road Object-Detection
Viaarxiv icon

FireCaffe: near-linear acceleration of deep neural network training on compute clusters

Add code
Jan 08, 2016
Figure 1 for FireCaffe: near-linear acceleration of deep neural network training on compute clusters
Figure 2 for FireCaffe: near-linear acceleration of deep neural network training on compute clusters
Figure 3 for FireCaffe: near-linear acceleration of deep neural network training on compute clusters
Figure 4 for FireCaffe: near-linear acceleration of deep neural network training on compute clusters
Viaarxiv icon

DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer

Add code
Oct 07, 2015
Figure 1 for DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
Figure 2 for DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
Figure 3 for DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
Figure 4 for DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
Viaarxiv icon