際際滷shows by User: jnhwkim / http://www.slideshare.net/images/logo.gif 際際滷shows by User: jnhwkim / Wed, 28 Jun 2017 01:51:25 GMT 際際滷Share feed for 際際滷shows by User: jnhwkim A summary of Categorical Reparameterization with Gumbel-Softmax by Jang et al. (ICLR 2017) /slideshow/a-summary-of-categorical-reparameterization-with-gumbelsoftmax-by-jang-et-al-iclr-2017/77320390 gumbel170616share-170628015125
A personal summary to share with lab mates. Please leave a comment to correct any error!]]>
A personal summary to share with lab mates. Please leave a comment to correct any error!]]> Wed, 28 Jun 2017 01:51:25 GMT /slideshow/a-summary-of-categorical-reparameterization-with-gumbelsoftmax-by-jang-et-al-iclr-2017/77320390 jnhwkim@slideshare.net(jnhwkim) A summary of Categorical Reparameterization with Gumbel-Softmax by Jang et al. (ICLR 2017) jnhwkim A personal summary to share with lab mates. Please leave a comment to correct any error! <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/gumbel170616share-170628015125-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> A personal summary to share with lab mates. Please leave a comment to correct any error!
A summary of Categorical Reparameterization with Gumbel-Softmax by Jang et al. (ICLR 2017) from Jin-Hwa Kim
]]> 254 2 https://cdn.slidesharecdn.com/ss_thumbnails/gumbel170616share-170628015125-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Multimodal Residual Networks for Visual QA /slideshow/multimodal-residual-networks-for-visual-qa/63546804 mrn9jun16-160629001055
Deep neural networks continue to advance the state-of-the-art of image recognition tasks with various methods. However, applications of these methods to multimodality remain limited. We present Multimodal Residual Networks (MRN) for the multimodal residual learning of visual question-answering, which extends the idea of the deep residual learning. Unlike the deep residual learning, MRN effectively learns the joint representation from vision and language information. The main idea is to use element-wise multiplication for the joint residual mappings exploiting the residual learning of the attentional models in recent studies. Various alternative models introduced by multimodality are explored based on our study. We achieve the state-of-the-art results on the Visual QA dataset for both Open-Ended and Multiple-Choice tasks. Moreover, we introduce a novel method to visualize the attention effect of the joint representations for each learning block using back-propagation algorithm, even though the visual features are collapsed without spatial information.]]>
Deep neural networks continue to advance the state-of-the-art of image recognition tasks with various methods. However, applications of these methods to multimodality remain limited. We present Multimodal Residual Networks (MRN) for the multimodal residual learning of visual question-answering, which extends the idea of the deep residual learning. Unlike the deep residual learning, MRN effectively learns the joint representation from vision and language information. The main idea is to use element-wise multiplication for the joint residual mappings exploiting the residual learning of the attentional models in recent studies. Various alternative models introduced by multimodality are explored based on our study. We achieve the state-of-the-art results on the Visual QA dataset for both Open-Ended and Multiple-Choice tasks. Moreover, we introduce a novel method to visualize the attention effect of the joint representations for each learning block using back-propagation algorithm, even though the visual features are collapsed without spatial information.]]> Wed, 29 Jun 2016 00:10:55 GMT /slideshow/multimodal-residual-networks-for-visual-qa/63546804 jnhwkim@slideshare.net(jnhwkim) Multimodal Residual Networks for Visual QA jnhwkim Deep neural networks continue to advance the state-of-the-art of image recognition tasks with various methods. However, applications of these methods to multimodality remain limited. We present Multimodal Residual Networks (MRN) for the multimodal residual learning of visual question-answering, which extends the idea of the deep residual learning. Unlike the deep residual learning, MRN effectively learns the joint representation from vision and language information. The main idea is to use element-wise multiplication for the joint residual mappings exploiting the residual learning of the attentional models in recent studies. Various alternative models introduced by multimodality are explored based on our study. We achieve the state-of-the-art results on the Visual QA dataset for both Open-Ended and Multiple-Choice tasks. Moreover, we introduce a novel method to visualize the attention effect of the joint representations for each learning block using back-propagation algorithm, even though the visual features are collapsed without spatial information. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/mrn9jun16-160629001055-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Deep neural networks continue to advance the state-of-the-art of image recognition tasks with various methods. However, applications of these methods to multimodality remain limited. We present Multimodal Residual Networks (MRN) for the multimodal residual learning of visual question-answering, which extends the idea of the deep residual learning. Unlike the deep residual learning, MRN effectively learns the joint representation from vision and language information. The main idea is to use element-wise multiplication for the joint residual mappings exploiting the residual learning of the attentional models in recent studies. Various alternative models introduced by multimodality are explored based on our study. We achieve the state-of-the-art results on the Visual QA dataset for both Open-Ended and Multiple-Choice tasks. Moreover, we introduce a novel method to visualize the attention effect of the joint representations for each learning block using back-propagation algorithm, even though the visual features are collapsed without spatial information.
Multimodal Residual Networks for Visual QA from Jin-Hwa Kim
]]> 265 4 https://cdn.slidesharecdn.com/ss_thumbnails/mrn9jun16-160629001055-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Simple, fast, and scalable torch7 tutorial /slideshow/simple-fast-and-scalable-torch7-tutorial/53136386 simplefastandscalabletorch7tutorial-150924024306-lva1-app6891
A tutorial based on basic information of Torch7. It covers installation, simple runable codes, tensor manipulations, sweep out key-packages and post-hoc audience q&a.]]>
A tutorial based on basic information of Torch7. It covers installation, simple runable codes, tensor manipulations, sweep out key-packages and post-hoc audience q&a.]]> Thu, 24 Sep 2015 02:43:06 GMT /slideshow/simple-fast-and-scalable-torch7-tutorial/53136386 jnhwkim@slideshare.net(jnhwkim) Simple, fast, and scalable torch7 tutorial jnhwkim A tutorial based on basic information of Torch7. It covers installation, simple runable codes, tensor manipulations, sweep out key-packages and post-hoc audience q&a. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/simplefastandscalabletorch7tutorial-150924024306-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> A tutorial based on basic information of Torch7. It covers installation, simple runable codes, tensor manipulations, sweep out key-packages and post-hoc audience q&amp;a.
Simple, fast, and scalable torch7 tutorial from Jin-Hwa Kim
]]> 144 6 https://cdn.slidesharecdn.com/ss_thumbnails/simplefastandscalabletorch7tutorial-150924024306-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Summary of Analogical Reinforcement Learning /jnhwkim/2-summary-of-analogical-reinforcement-learning 2summaryofanalogicalreinforcementlearning-131123005052-phpapp01
original paper is here. http://matt.colorado.edu/papers/foster-jones-cogsci13.pdf]]>
original paper is here. http://matt.colorado.edu/papers/foster-jones-cogsci13.pdf]]> Sat, 23 Nov 2013 00:50:52 GMT /jnhwkim/2-summary-of-analogical-reinforcement-learning jnhwkim@slideshare.net(jnhwkim) Summary of Analogical Reinforcement Learning jnhwkim original paper is here. http://matt.colorado.edu/papers/foster-jones-cogsci13.pdf <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2summaryofanalogicalreinforcementlearning-131123005052-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> original paper is here. http://matt.colorado.edu/papers/foster-jones-cogsci13.pdf
Summary of Analogical Reinforcement Learning from Jin-Hwa Kim
]]> 217 2 https://cdn.slidesharecdn.com/ss_thumbnails/2summaryofanalogicalreinforcementlearning-131123005052-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Summary of disorders of voluntary movement /slideshow/summary-of-disorders-of-voluntary-movement/27904922 summaryofdisordersofvoluntarymovement-131104182426-phpapp02
Clinical Neuropsychology: A Practical Guide to Assessment and Management for Clinicians Summary of Chapter 10. Disorders of Voluntary Movement http://as.wiley.com/WileyCDA/WileyTitle/productCd-0470683716.html]]>
Clinical Neuropsychology: A Practical Guide to Assessment and Management for Clinicians Summary of Chapter 10. Disorders of Voluntary Movement http://as.wiley.com/WileyCDA/WileyTitle/productCd-0470683716.html]]> Mon, 04 Nov 2013 18:24:26 GMT /slideshow/summary-of-disorders-of-voluntary-movement/27904922 jnhwkim@slideshare.net(jnhwkim) Summary of disorders of voluntary movement jnhwkim Clinical Neuropsychology: A Practical Guide to Assessment and Management for Clinicians Summary of Chapter 10. Disorders of Voluntary Movement http://as.wiley.com/WileyCDA/WileyTitle/productCd-0470683716.html <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/summaryofdisordersofvoluntarymovement-131104182426-phpapp02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Clinical Neuropsychology: A Practical Guide to Assessment and Management for Clinicians Summary of Chapter 10. Disorders of Voluntary Movement http://as.wiley.com/WileyCDA/WileyTitle/productCd-0470683716.html
Summary of disorders of voluntary movement from Jin-Hwa Kim
]]> 239 2 https://cdn.slidesharecdn.com/ss_thumbnails/summaryofdisordersofvoluntarymovement-131104182426-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Summary of a neural model of human image categorization /slideshow/summary-of-a-neural-model-of-human-image-categorization/27644790 1summaryofaneuralmodelofhumanimagecategorization-131028070216-phpapp02
original paper is in here: http://compneuro.uwaterloo.ca/publications/hunsberger2013a.html Summary of one of CogSci 2013 papers. It demonstrates how to examine the computational model as an imitation of human's image categorization.]]>
original paper is in here: http://compneuro.uwaterloo.ca/publications/hunsberger2013a.html Summary of one of CogSci 2013 papers. It demonstrates how to examine the computational model as an imitation of human's image categorization.]]> Mon, 28 Oct 2013 07:02:16 GMT /slideshow/summary-of-a-neural-model-of-human-image-categorization/27644790 jnhwkim@slideshare.net(jnhwkim) Summary of a neural model of human image categorization jnhwkim original paper is in here: http://compneuro.uwaterloo.ca/publications/hunsberger2013a.html Summary of one of CogSci 2013 papers. It demonstrates how to examine the computational model as an imitation of human's image categorization. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/1summaryofaneuralmodelofhumanimagecategorization-131028070216-phpapp02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> original paper is in here: http://compneuro.uwaterloo.ca/publications/hunsberger2013a.html Summary of one of CogSci 2013 papers. It demonstrates how to examine the computational model as an imitation of human&#39;s image categorization.
Summary of a neural model of human image categorization from Jin-Hwa Kim
]]> 311 2 https://cdn.slidesharecdn.com/ss_thumbnails/1summaryofaneuralmodelofhumanimagecategorization-131028070216-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 JavaScript Closures for Dummies & JavaScript prototype, closures and OOP. /slideshow/java-script-cut/20288444 javascriptcut-130430193153-phpapp01
Summary of Morris Johns' blog article and My practical examples.]]>
Summary of Morris Johns' blog article and My practical examples.]]> Tue, 30 Apr 2013 19:31:53 GMT /slideshow/java-script-cut/20288444 jnhwkim@slideshare.net(jnhwkim) JavaScript Closures for Dummies & JavaScript prototype, closures and OOP. jnhwkim Summary of Morris Johns' blog article and My practical examples. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/javascriptcut-130430193153-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Summary of Morris Johns&#39; blog article and My practical examples.
JavaScript Closures for Dummies & JavaScript prototype, closures and OOP. from Jin-Hwa Kim
]]> 1421 2 https://cdn.slidesharecdn.com/ss_thumbnails/javascriptcut-130430193153-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-jnhwkim-48x48.jpg?cb=1523173906 https://cdn.slidesharecdn.com/ss_thumbnails/gumbel170616share-170628015125-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/a-summary-of-categorical-reparameterization-with-gumbelsoftmax-by-jang-et-al-iclr-2017/77320390 A summary of Categoric... https://cdn.slidesharecdn.com/ss_thumbnails/mrn9jun16-160629001055-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/multimodal-residual-networks-for-visual-qa/63546804 Multimodal Residual Ne... https://cdn.slidesharecdn.com/ss_thumbnails/simplefastandscalabletorch7tutorial-150924024306-lva1-app6891-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/simple-fast-and-scalable-torch7-tutorial/53136386 Simple, fast, and scal...