Learning to combine foveal glimpses with a third-order Boltzmann machine

Keywords

Foveal, Computer science, Artificial intelligence, Boltzmann machine, Pixel

References

• Peripheral-Foveal Vision for Real-time Object Recognition and Tracking in VideoStephen Jay Gould, Joakim Arfvidsson, Adrian Kaehler — 2007
• Treatise on Physiological OpticsHermann von Helmholtz, P. C. Southall — 1962
• Classification using discriminative restricted Boltzmann machinesHugo Larochelle, Yoshua Bengio — 2008
• An empirical evaluation of deep architectures on problems with many factors of variationHugo Larochelle, Dumitru Erhan, Aaron Courville — 2007
• Robust classification of objects, faces, and flowers using natural image statisticsChristopher Kanan, Garrison W. Cottrell — 2010
• A Computational Model of Eye Movements during Object Class DetectionWei Zhang, Hyejin Yang, Dimitris Samaras — 2005
• An Information Maximization Model of Eye MovementsLaura Renninger, James M. Coughlan, Preeti Verghese — 2004
• Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search.Antonio Torralba, Aude Oliva, Monica S. Castelhano — 2006
• Factored conditional restricted Boltzmann Machines for modeling motion styleGraham W. Taylor, Geoffrey E. Hinton — 2009
• Training Products of Experts by Minimizing Contrastive DivergenceGeoffrey E. Hinton — 2002
• Learning to represent visual inputGeoffrey E. Hinton — 2010
• Unsupervised Learning of Image TransformationsRoland Memisevic, Geoffrey E. Hinton — 2007
• View-invariant object category learning, recognition, and search: how spatial and object attention are coordinated using surface-based attentional shrouds.Arash Fazl, Stephen Grossberg, Ennio Mingolla — 2009
• A Model of Saliency-Based Visual Attention for Rapid Scene AnalysisLaurent Itti, Christof Koch, Ernst Niebur — 1998
• Selective Attention for Handwritten Digit RecognitionEthem Alpaydın — 1995
• Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann MachinesRoland Memisevic, Geoffrey E. Hinton — 2010
• Q-learning of sequential attention for visual object recognition from informative local descriptorsLucas Paletta, Gerald Fritz, Christin Seifert — 2005
• Computational modelling of visual attentionLaurent Itti, Christof Koch — 2001
• Exploring Strategies for Training Deep Neural NetworksLarochelleHugo, BengioYoshua, LouradourJérôme — 2009
• Modeling Saccadic Targeting in Visual SearchRajesh P. N. Rao, Gregory J. Zelinsky, Mary Hayhoe — 1995

Cited by

• Multiple Instance Reinforcement Learning for Efficient Weakly-Supervised Detection in ImagesStefan Mathe, Cristian Sminchisescu — 2014
• Deep Boltzmann Machines as Hierarchical Generative Models of Perceptual Inference in the CortexDavid Reichert — 2012
• Apprentissage de représentations et robotique développementale : quelques apports de l'apprentissage profond pour la robotique autonome. (Representation learning and developmental robotics : on the use of deep learning for autonomous robots)Alain Droniou — 2015
• WordRank: Learning Word Embeddings via Robust RankingShihao Ji, Hyokun Yun, Pinar Yanardag — 2015
• Sequential prediction for budgeted learning : Application to trigger design. (Prédiction séquentielle pour l'apprentissage budgété : Application à la conception de trigger)Djalel Benbouzid — 2014
• A syntactic approach to robot learning of human tasks from demonstrationsKyuhwa Lee — 2013
• Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionKelvin Xu, Jimmy Ba, Ryan Kiros — 2015
• Gated Autoencoders with Tied Input WeightsAlain Droniou, Olivier Sigaud — 2013
• Object detection through search with a foveated visual systemEmre Akbaş, Miguel P. Eckstein — 2014
• Bootstrapping vehicles : a formal approach to unsupervised sensorimotor learning based on invarianceAndrea Censi — 2013
• Invariant visual object recognition: biologically plausible approachesLeigh Robinson, Edmund T. Rolls — 2015
• On Learning Where To LookMarc’Aurelio Ranzato — 2014
• Describing Multimedia Content Using Attention-Based Encoder-Decoder NetworksKyunghyun Cho, Aaron Courville, Yoshua Bengio — 2015
• An active search strategy for efficient object class detectionAbel Gonzalez-Garcia, Alexander Vezhnevets, Vittorio Ferrari — 2014
• STARE: Spatio-Temporal Attention Relocation for Multiple Structured Activities DetectionKyuhwa Lee, Dimitri Ognibene, Hyung Jin Chang — 2015
• Learning to Relate ImagesRoland Memisevic — 2011
• A Neural Autoregressive Approach to Attention-based RecognitionYin Zheng, Richard S. Zemel, Yu‐Jin Zhang — 2015
• On-line deep learning method for action recognitionKonstantinos Charalampous, Αντώνιος Γαστεράτος — 2016
• Active Object Recognition with a Space-Variant RetinaChristopher Kanan — 2013
• Gradient-based learning of higher-order image featuresRoland Memisevic — 2011

Related papers

• Deep Residual Learning for Image RecognitionKaiming He, Xiangyu Zhang, Shaoqing Ren — 2015
• ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton — 2012
• Learning Where to Attend with Deep Architectures for Image TrackingMisha Denil, Loris Bazzani, Hugo Larochelle — 2011
• Recurrent Models of Visual AttentionVolodymyr Mnih, Nicolas Heess, Alex Graves — 2014
• A Model of Saliency-Based Visual Attention for Rapid Scene AnalysisLaurent Itti, Christof Koch, Ernst Niebur — 1998