Add to ORKGThe ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify the output sensitivity to the parameters (ie their relevance to the network output) and introduce a regularization term that gradually lowers the absolute value of parameters with low sensitivity. Thus, a very large fraction of the parameters approach zero and are eventually set to zero by simple thresholding. Our method surpasses most of the recent techniques both in terms of sparsity and error rates. In some cases, the method reaches twice the sparsity obtained by other techniques at equal error rates
Brain-inspired event-driven processors execute deep neural networks (DNNs) in a sparsity-aware manne...
In this paper, we address the challenging task of simultaneously optimizing (i) the weights of a neu...
The undeniable computational power of artificial neural networks has granted the scientific communit...
Deep neural networks include millions of learnable parameters, making their deployment over resource...
Structural neural network pruning aims to remove the redundant channels in the deep convolutional ne...
Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applic...
Deep Neural Networks have memory and computational demands that often render them difficult to use i...
The growing energy and performance costs of deep learning have driven the community to reduce the si...
Deep learning is becoming more widespread due to its power in solving complex classification problem...
Although increasing model size can enhance the adversarial robustness of deep neural networks, in re...
International audienceSparsifying deep neural networks is of paramount interest in many areas, espec...
Deep learning has been empirically successful in recent years thanks to the extremely over-parameter...
In this paper, we address the challenging task of simultaneously optimizing (i) the weights of a neu...
The training of sparse neural networks is becoming an increasingly important tool for reducing the ...
Deep neural networks (DNN) are the state-of-the-art machine learning models outperforming traditiona...
Brain-inspired event-driven processors execute deep neural networks (DNNs) in a sparsity-aware manne...
In this paper, we address the challenging task of simultaneously optimizing (i) the weights of a neu...
The undeniable computational power of artificial neural networks has granted the scientific communit...
Deep neural networks include millions of learnable parameters, making their deployment over resource...
Structural neural network pruning aims to remove the redundant channels in the deep convolutional ne...
Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applic...
Deep Neural Networks have memory and computational demands that often render them difficult to use i...
The growing energy and performance costs of deep learning have driven the community to reduce the si...
Deep learning is becoming more widespread due to its power in solving complex classification problem...
Although increasing model size can enhance the adversarial robustness of deep neural networks, in re...
International audienceSparsifying deep neural networks is of paramount interest in many areas, espec...
Deep learning has been empirically successful in recent years thanks to the extremely over-parameter...
In this paper, we address the challenging task of simultaneously optimizing (i) the weights of a neu...
The training of sparse neural networks is becoming an increasingly important tool for reducing the ...
Deep neural networks (DNN) are the state-of-the-art machine learning models outperforming traditiona...
Brain-inspired event-driven processors execute deep neural networks (DNNs) in a sparsity-aware manne...
In this paper, we address the challenging task of simultaneously optimizing (i) the weights of a neu...
The undeniable computational power of artificial neural networks has granted the scientific communit...