Efficient Architecture Search by Network Transformation

Keywords

Computer science, Benchmark (surveying), Reinforcement learning, Architecture, Network architecture

References

• On the importance of initialization and momentum in deep learningIlya Sutskever, James Martens, George E. Dahl — 2013
• Training Very Deep NetworksRupesh K. Srivastava, Klaus Greff, Jürgen Schmidhuber — 2015
• Designing Neural Networks using Genetic AlgorithmsGeoffrey F. Miller, Peter M. Todd, Shailesh Hegde — 1989
• Very Deep Convolutional Networks for Large-Scale Image RecognitionKaren Simonyan, Andrew Zisserman — 2014
• Scalable Bayesian Optimization Using Deep Neural NetworksJasper Snoek, Oren Rippel, Kevin Swersky — 2015
• Algorithms for Hyper-Parameter OptimizationJames Bergstra, Yoshua Bengio — 2011
• Evolving Neural Networks through Augmenting TopologiesKenneth O. Stanley, Risto Miikkulainen — 2002
• Reinforcement Learning: An IntroductionSutton, Richard S, Barto, Andrew G — 1998
• A Natural Policy GradientSham M. Kakade — 2001
• Practical Bayesian Optimization of Machine Learning AlgorithmsJasper Snoek, Hugo Larochelle, Ryan P. Adams — 2012
• Bidirectional recurrent neural networksMike Schuster, Kuldip K. Paliwal — 1997
• A Perspective View and Survey of Meta-LearningRicardo Vilalta, Youssef Drissi — 2002
• ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton — 2012
• Net2Net: Accelerating Learning via Knowledge TransferTianqi Chen, Ian Goodfellow, Jonathon Shlens — 2015
• Deep Residual Learning for Image RecognitionKaiming He, Xiangyu Zhang, Shaoqing Ren — 2015
• Mastering the game of Go with deep neural networks and tree searchDavid Silver, Aja Huang, Chris J. Maddison — 2016
• Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning CurvesTobias Domhan, Jost Tobias Springenberg, Frank Hutter — 2015
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed SystemsMartı́n Abadi, Ashish Agarwal, Paul Barham — 2016
• Maxout NetworksIan Goodfellow, David Warde-Farley, Mehdi Mirza — 2013
• Reading Digits in Natural Images with Unsupervised Feature LearningYuval Netzer — 2011

Cited by

• A genetic programming approach to designing convolutional neural network architecturesMasanori Suganuma, Shinichi Shirakawa, Tomoharu Nagao — 2017
• Transfer Learning to Learn with Multitask Neural Model SearchCatherine Wong, Andréa Gesmundo — 2017
• Progressive Neural Architecture SearchChenxi Liu, Barret Zoph, Maxim Neumann — 2017
• Regularized Evolution for Image Classifier Architecture SearchEsteban Real, Alok Aggarwal, Yanping Huang — 2018
• ADC: Automated Deep Compression and Acceleration with Reinforcement LearningYihui He, Song Han — 2018
• Fast Neural Architecture Construction using EnvelopeNetsPurushotham Kamath, Abhishek Singh, Debo Dutta — 2018
• Efficient image dataset classification difficulty estimation for predicting deep-learning accuracyFlorian Scheidegger, Roxana Istrate, Giovanni Mariani — 2018
• Multi-objective Architecture Search for CNNsThomas Elsken, Jan Hendrik Metzen, Frank Hutter — 2018
• Path-Level Network Transformation for Efficient Architecture SearchHan Cai, Jiacheng Yang, Weinan Zhang — 2018
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree SearchLinnan Wang, Yiyang Zhao, Yuu Jinnai — 2019
• TAPAS: Train-less Accuracy Predictor for Architecture SearchRoxana Istrate, Florian Scheidegger, Giovanni Mariani — 2018
• Speeding up the Hyperparameter Optimization of Deep Convolutional Neural NetworksTobias Hinz, Nicolás Navarro-Guerrero, Sven Magg — 2018
• Efficient Neural Architecture Search with Network MorphismHaifeng Jin, Qingquan Song, Xia Hu — 2018
• MONAS: Multi-Objective Neural Architecture Search using Reinforcement LearningChi-Hung Hsu, Chang, Shu-Huan, Jhao-Hong Liang — 2018
• Auto Deep Compression by Reinforcement Learning Based Actor-Critic StructureHamed Hakkak — 2018
• Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter SearchArber Zela, Aaron Klein, Stefan Falkner — 2018
• BlockQNN: Efficient Block-Wise Neural Network Architecture GenerationZhao Zhong, Zichen Yang, Boyang Deng — 2018
• Adaptive Neural TreesRyutaro Tanno, Kai Arulkumaran, Daniel C. Alexander — 2018
• Reinforced Evolutionary Neural Architecture SearchYukang Chen, Gaofeng Meng, Qian Zhang — 2018
• Automatically Designing CNN Architectures Using the Genetic Algorithm for Image ClassificationYanan Sun, Bing Xue, Mengjie Zhang — 2018

Related papers

• Design Space Exploration of a Sparse MobileNetV2 Using High-Level Synthesis and Sparse Matrix Techniques on FPGAsAntonios Tragoudaras, Pavlos Stoikos, Konstantinos Fanaras — 2022
• ImageSpec: Efficient High-Level Synthesis of Image Processing ApplicationsAbdul Khader Thalakkattu Moosa, Nilotpola Sarma, Chandan Karfa — 2022
• An Evaluation and Architecture Exploration Engine for CNN Accelerators through Extensive Dataflow AnalysisShan-Hui Chou, Ting-Yun Hsiao, Jing-Yang Jou — 2023
• NNest: Early-Stage Design Space Exploration Tool for Neural Network Inference AcceleratorsLiu Ke, Xin He, Xuan Zhang — 2018
• Integrating Quick Resource Estimators in Hardware Construction Framework for Design Space ExplorationBruno Ferres, Olivier Muller, Frederic Rousseau — 2021
• Using PredictiveModeling for Cross-Program Design Space Exploration in Multicore SystemsSalman A. Khan, Polychronis Xekalakis, John Cavazos — 2007
• Datapath Optimization for Embedded Signal Processing Architectures utilizing Design Space ExplorationJohannes Knödtel, Marc Reichenbach — 2023
• FEECA: Design Space Exploration for Low-Latency and Energy-Efficient Capsule Network AcceleratorsAlberto Marchisio, Vojtěch Mrázek, Muhammad Abdullah Hanif — 2021