Open AccessPosted Content
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Jonathan Frankle,Michael Carbin +1 more
Reads0
Chats0
TLDR
In this paper, the lottery tickets hypothesis is proposed to find the subnetworks that can reach test accuracy comparable to the original network in a similar number of iterations, where the winning tickets have won the initialization lottery: their connections have initial weights that make training particularly effective.Abstract:
Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance.
We find that a standard pruning technique naturally uncovers subnetworks whose initializations made them capable of training effectively. Based on these results, we articulate the "lottery ticket hypothesis:" dense, randomly-initialized, feed-forward networks contain subnetworks ("winning tickets") that - when trained in isolation - reach test accuracy comparable to the original network in a similar number of iterations. The winning tickets we find have won the initialization lottery: their connections have initial weights that make training particularly effective.
We present an algorithm to identify winning tickets and a series of experiments that support the lottery ticket hypothesis and the importance of these fortuitous initializations. We consistently find winning tickets that are less than 10-20% of the size of several fully-connected and convolutional feed-forward architectures for MNIST and CIFAR10. Above this size, the winning tickets that we find learn faster than the original network and reach higher test accuracy.read more
Citations
More filters
Journal ArticleDOI
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
Alejandro Barredo Arrieta,Natalia Díaz-Rodríguez,Javier Del Ser,Javier Del Ser,Adrien Bennetot,Adrien Bennetot,Siham Tabik,Alberto Barbado,Salvador García,Sergio Gil-Lopez,Daniel Molina,Richard Benjamins,Raja Chatila,Francisco Herrera +13 more
TL;DR: In this paper, a taxonomy of recent contributions related to explainability of different machine learning models, including those aimed at explaining Deep Learning methods, is presented, and a second dedicated taxonomy is built and examined in detail.
Posted Content
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.
Alejandro Barredo Arrieta,Natalia Díaz-Rodríguez,Javier Del Ser,Javier Del Ser,Adrien Bennetot,Adrien Bennetot,Siham Tabik,Alberto Barbado,Salvador García,Sergio Gil-Lopez,Daniel Molina,Richard Benjamins,Raja Chatila,Francisco Herrera +13 more
TL;DR: Previous efforts to define explainability in Machine Learning are summarized, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought, and a taxonomy of recent contributions related to the explainability of different Machine Learning models are proposed.
Posted Content
Rethinking the Value of Network Pruning
TL;DR: It is found that with optimal learning rate, the "winning ticket" initialization as used in Frankle & Carbin (2019) does not bring improvement over random initialization, and the need for more careful baseline evaluations in future research on structured pruning methods is suggested.
Posted Content
A Primer in BERTology: What we know about how BERT works
TL;DR: This paper is the first survey of over 150 studies of the popular BERT model, reviewing the current state of knowledge about how BERT works, what kind of information it learns and how it is represented, common modifications to its training objectives and architecture, the overparameterization issue, and approaches to compression.
Proceedings ArticleDOI
Revealing the Dark Secrets of BERT
TL;DR: It is shown that manually disabling attention in certain heads leads to a performance improvement over the regular fine-tuned BERT models, indicating the overall model overparametrization.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.