Bayesian optimization on graph-structured search spaces: Optimizing deep multimodal fusion architectures

Augasta, 2013, Pruning algorithms of neural networks — a comparative study, Cent. Eur. J. Comput. Sci., 3, 105 B. Baker, O. Gupta, N. Naik, R. Raskar, Designing neural network architectures using reinforcement learning, arXiv preprint arXiv:1611.02167 (2016). Bergstra, 2012, Random search for hyper-parameter optimization, J. Mach. Learn. Res., 13, 281 Bergstra, 2011, Algorithms for hyper-parameter optimization, 2546 Chaquet, 2013, A survey of video datasets for human action and activity recognition, Comput. Vis. Image Underst., 117, 633, 10.1016/j.cviu.2013.01.013 T. Chen, I. Goodfellow, J. Shlens, Net2Net: accelerating learningvia knowledge transfer, ArXiv e-prints arXiv:1511.05641 (2015). Ding, 2013, Evolutionary artificial neural networks: a review, Artif. Intell. Rev., 39, 251, 10.1007/s10462-011-9270-6 Elman, 1993, Learning and development in neural networks: the importance of starting small, Cognition, 48, 71, 10.1016/0010-0277(93)90058-4 Escalera, 2014, Chalearn looking at people challenge 2014: dataset and results Feng, 2015, Learning the structure of deep convolutional networks, 2749 T. Ganegedara, L. Ott, F. Ramos, Online adaptation of deep architectures with reinforcement learning, arXiv preprint arXiv:1608.02292 (2016). Han, 2015, Learning both weights and connections for efficient neural network, 1135 E. Hazan, A. Klivans, Y. Yuan, Hyperparameter optimization: a spectral ap-proach, arXiv preprint arXiv:1706.00764 (2017). He, 2016, Deep residual learning for image recognition F. Hutter, H.H. Hoos, K. Leyton-Brown, Sequential Model-Based Optimization for General Algorithm Configuration, Springer, Berlin, Heidelberg, pp. 507–523. Kulkarni, 2015, Learning the structure of deep architectures using L1 regularization Kwok, 1997, Constructive algorithms for structure learning in feedforward neural networks for regression problems, IEEE Trans. Neural Netw., 8, 630, 10.1109/72.572102 Lafferty, 2002, Diffusion kernels on graphs and other discrete structures, 315 Li, 2017, Modout: learning multi-modal architectures by stochastic regularization, 422 L. Li, K. Jamieson, G. DeSalvo, A. Rostamizadeh, A. Talwalkar, Hyperband: a novel bandit-based approach to hyperparameter optimization, arXiv preprint arXiv:1603.06560 (2016). R. Miikkulainen, J. Liang, E. Meyerson, A. Rawal, D. Fink, O. Francon, B. Raju, A. Navruzyan, N. Duffy, B. Hodjat, Evolving deep neural networks, arXiv preprint arXiv:1703.00548 (2017). Murdock, 2016, Blockout: dynamic model selection for hierarchical deep networks Navarin, 2017, Approximated neighbours minhash graph node kernel, 281 Neuhaus, 2006, Edit distance-based kernel functions for structural pattern classification, Pattern Recogn., 39, 1852, 10.1016/j.patcog.2006.04.012 Neverova, 2015, Moddrop: adaptive multi-modal gesture recognition, IEEE Trans. Pattern Anal. Mach. Intell., PP Ngiam, 2011, Multimodal deep learning, 689 Ojha, 2017, Metaheuristic design of feedforward neural networks: a review of two decades of research, Eng. Appl. Artif. Intell., 60, 97, 10.1016/j.engappai.2017.01.013 Rasmussen, 2006 E. Real, S. Moore, A. Selle, S. Saxena, Y.L. Suematsu, Q. Le, A. Kurakin, Large-scale evolution of image classifiers, arXiv preprint arXiv:1703.01041 (2017). Reiss, 2012, Introducing a new benchmarked dataset for activity monitoring Ruffieux, 2014, A survey of datasets for human gesture recognition, 337 Shahriari, 2016, Taking the human out of the loop: a review of Bayesian optimization, Proc. IEEE, 104, 148, 10.1109/JPROC.2015.2494218 Sitova, 2016, HMOG: new behavioral biometric features for continuous authentication of smartphone users, IEEE Trans. Inf. Forensics Secur., 11, 877, 10.1109/TIFS.2015.2506542 Srivastava, 2014, Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15, 1929 Srivastava, 2012, Multimodal learning with deep Boltzmann machines, 2222 Stanley, 2002, Evolving neural networks through augmenting topologies, Evol. Comput., 10, 99, 10.1162/106365602320169811 Sung, 2011, Human activity detection from RGBD images Sung, 2012, Unstructured human activity detection from RGBD images, 842 Szegedy, 2015, Going deeper with convolutions, 1 P. Verbancsics, J. Harguess, Generative neuroevolution for deep learning, arXiv preprint arXiv:1312.5355 (2013). Vishwanathan, 2010, Graph kernels, J. Mach. Learn. Res., 11, 1201 Z. Wang, C. Gehring, P. Kohli, S. Jegelka, Ensemble Bayesian optimization, arXiv preprint arXiv:1706.01445 (2017). Wen, 2016, Learning structured sparsity in deep neural networks, 2074 Yang, 2014, A structure optimization algorithm of neural networks for large-scale data sets, 956 Yao, 1993, A review of evolutionary artificial neural networks, Int. J. Intell. Syst., 8, 539, 10.1002/int.4550080406 Zoph, 2017, Neural architecture search with reinforcement learning