paper-with-me

홈 › Papers

Do Deep Nets Really Need to be Deep?

2013-12-21 · NeurIPS 2014 12 · Lei Jimmy Ba, Rich Caruana

Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision. In this extended abstract, we show that shallow feed-forward networks can learn the complex functions previously learned by deep nets and achieve accuracies previously only achievable with deep models. Moreover, in some cases the shallow neural nets can learn these deep functions using a total number of parameters similar to the original deep model. We evaluate our method on the TIMIT phoneme recognition task and are able to train shallow fully-connected nets that perform similarly to complex, well-engineered, deep convolutional architectures. Our success in training shallow neural nets to mimic deeper models suggests that there probably exist better algorithms for training shallow feed-forward nets than those currently available.

📄 PDF Abstract BibTeX arXiv:1312.6184

Code (2)

jchen98/compression tf
peta78/linear-regression-voting-and-statistics

Tasks

Phoneme Recognitionspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Do Deep Convolutional Nets Really Need to be Deep and Convolutional?

2016-03-17 · Gregor Urban, Krzysztof J. Geras, Samira Ebrahimi Kahou, Ozlem Aslan 외

Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or sh…

AdderNet: Do We Really Need Multiplications in Deep Learning?

2019-12-31 · CVPR 2020 6 · Hanting Chen, Yunhe Wang, Chunjing Xu, Boxin Shi 외

Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity betw…

Deep Learning

Deep Residual Networks and Weight Initialization

2017-09-09 · Masato Taki

Residual Network (ResNet) is the state-of-the-art architecture that realizes successful training of really deep neural network. It is also known that good weight initialization of neural network avoids problem of vanishi…

Dynamic Routing Networks

2019-05-13 · Shaofeng Cai, Yao Shu, Wei Wang, Beng Chin Ooi

The deployment of deep neural networks in real-world applications is mostly restricted by their high inference costs. Extensive efforts have been made to improve the accuracy with expert-designed or algorithm-searched ar…

Neural Architecture Search

Convolutional Networks with Adaptive Inference Graphs

2017-11-30 · ECCV 2018 9 · Andreas Veit, Serge Belongie

Do convolutional networks really need a fixed feed-forward structure? What if, after identifying the high-level concept of an image, a network could move directly to a layer that can distinguish fine-grained differences?…