Open AccessPosted Content
Neural Architecture Search with Reinforcement Learning
Barret Zoph,Quoc V. Le +1 more
TLDR
This paper uses a recurrent network to generate the model descriptions of neural networks and trains this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set.Abstract:
Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy. Our CIFAR-10 model achieves a test error rate of 3.65, which is 0.09 percent better and 1.05x faster than the previous state-of-the-art model that used a similar architectural scheme. On the Penn Treebank dataset, our model can compose a novel recurrent cell that outperforms the widely-used LSTM cell, and other state-of-the-art baselines. Our cell achieves a test set perplexity of 62.4 on the Penn Treebank, which is 3.6 perplexity better than the previous state-of-the-art model. The cell can also be transferred to the character language modeling task on PTB and achieves a state-of-the-art perplexity of 1.214.read more
Citations
More filters
Journal ArticleDOI
Improving Extreme Low-Bit Quantization With Soft Threshold
TL;DR: Xu et al. as mentioned in this paper proposed a soft threshold from ternarization to arbitrary bit-width, named Soft Threshold Quantized Networks (STQN), which enables the model to automatically determine ternarized values instead of depending on a hard threshold.
Journal ArticleDOI
Make Your Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning
Baohao Liao,Shaomu Tan,C. Monz +2 more
TL;DR: Memory-efficient fine-tuning (MEFT) as discussed by the authors inserts adapters into a pre-trained language model, preserving the PLM's starting point and making it reversible without additional pre-training.
Journal ArticleDOI
Transformers with Learnable Activation Functions
TL;DR: This paper investigates the effectiveness of using Rational Activation Function (RAF) that is a learnable activation function in the Transformer architecture and opens a new research direction for analyzing and interpreting pre-trained models according to the learned activation functions.
Journal ArticleDOI
Towards Self-supervised and Weight-preserving Neural Architecture Search
TL;DR: The self-supervised and weight-preserving neural architecture search (SSWP-NAS) is proposed as an extension of the current NAS framework by allowing the self- supervision and retaining the concomitant weights discovered during the search stage to simplify the workflow of NAS to a one-stage and proxy-free procedure.
Posted Content
Regularized Evolutionary Population-Based Training
TL;DR: In this paper, an algorithm called Evolutionary Population-Based Training (EPBT) is proposed that interleaves the training of a DNN's weights with the metalearning of loss functions.
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.
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.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.