-
Deeplite Neutrino: An End-to-End Framework for Constrained Deep Learning Model Optimization
Designing deep learning-based solutions is becoming a race for training ...
01/11/2021 ∙ by Anush Sankaran, et al. ∙
20
∙
share
read it
-
DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems
Learning deep representations to solve complex machine learning tasks ha...
12/02/2020 ∙ by Vincent Gripon, et al. ∙
0
∙
share
read it
-
ThriftyNets : Convolutional Neural Networks with Tiny Parameter Budget
Typical deep convolutional architectures present an increasing number of...
07/20/2020 ∙ by Guillaume Coiffier, et al. ∙
0
∙
share
read it
-
BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization
Neural networks have demonstrably achieved state-of-the art accuracy usi...
02/08/2020 ∙ by Milos Nikolic, et al. ∙
15
∙
share
read it
-
Training Modern Deep Neural Networks for Memory-Fault Robustness
Because deep neural networks (DNNs) rely on a large number of parameters...
11/23/2019 ∙ by Ghouthi Boukli Hacene, et al. ∙
0
∙
share
read it
-
Efficient Hardware Implementation of Incremental Learning and Inference on Chip
In this paper, we tackle the problem of incrementally learning a classif...
11/18/2019 ∙ by Ghouthi Boukli Hacene, et al. ∙
0
∙
share
read it
-
Deep geometric knowledge distillation with graphs
In most cases deep learning architectures are trained disregarding the a...
11/08/2019 ∙ by Carlos Lassance, et al. ∙
26
∙
share
read it
-
Attention Based Pruning for Shift Networks
In many application domains such as computer vision, Convolutional Layer...
05/29/2019 ∙ by Ghouthi Boukli Hacene, et al. ∙
0
∙
share
read it
-
Introducing Graph Smoothness Loss for Training Deep Learning Architectures
We introduce a novel loss function for training deep learning architectu...
05/01/2019 ∙ by Myriam Bontonou, et al. ∙
20
∙
share
read it
-
Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are state-of-the-art in numerous co...
12/29/2018 ∙ by Ghouthi Boukli Hacene, et al. ∙
0
∙
share
read it
-
Transfer Incremental Learning using Data Augmentation
Deep learning-based methods have reached state of the art performances, ...
10/04/2018 ∙ by Ghouthi Boukli Hacene, et al. ∙
0
∙
share
read it
