ºÝºÝߣshows by User: ssuserb667a8 / http://www.slideshare.net/images/logo.gif ºÝºÝߣshows by User: ssuserb667a8 / Thu, 05 Mar 2020 05:58:52 GMT ºÝºÝߣShare feed for ºÝºÝߣshows by User: ssuserb667a8 Learning visual representation without human label /slideshow/learning-visual-representation-without-human-label/229715973 learningvisualrepresentationwithouthuman-label-200305055852
Self supervised learning (SSL) is one of the most fast-growing research topic in recent years. SSL provides algorithm that directly learn visual representation from data itself rather than human manual labels. From theoretical point of view, SSL explores information theory & the nature of large scale dataset.]]>
Self supervised learning (SSL) is one of the most fast-growing research topic in recent years. SSL provides algorithm that directly learn visual representation from data itself rather than human manual labels. From theoretical point of view, SSL explores information theory & the nature of large scale dataset.]]> Thu, 05 Mar 2020 05:58:52 GMT /slideshow/learning-visual-representation-without-human-label/229715973 ssuserb667a8@slideshare.net(ssuserb667a8) Learning visual representation without human label ssuserb667a8 Self supervised learning (SSL) is one of the most fast-growing research topic in recent years. SSL provides algorithm that directly learn visual representation from data itself rather than human manual labels. From theoretical point of view, SSL explores information theory & the nature of large scale dataset. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/learningvisualrepresentationwithouthuman-label-200305055852-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Self supervised learning (SSL) is one of the most fast-growing research topic in recent years. SSL provides algorithm that directly learn visual representation from data itself rather than human manual labels. From theoretical point of view, SSL explores information theory &amp; the nature of large scale dataset.
Learning visual representation without human label from Kai-Wen Zhao
]]> 1093 0 https://cdn.slidesharecdn.com/ss_thumbnails/learningvisualrepresentationwithouthuman-label-200305055852-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 Deep Double Descent /slideshow/deep-double-descent/207536470 ddd-191219042605
A new paper published by OpenAI discussing generalization in deep learning and provide an observation that how model & data complexity influence each other. ]]>
A new paper published by OpenAI discussing generalization in deep learning and provide an observation that how model & data complexity influence each other. ]]> Thu, 19 Dec 2019 04:26:05 GMT /slideshow/deep-double-descent/207536470 ssuserb667a8@slideshare.net(ssuserb667a8) Deep Double Descent ssuserb667a8 A new paper published by OpenAI discussing generalization in deep learning and provide an observation that how model & data complexity influence each other. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ddd-191219042605-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> A new paper published by OpenAI discussing generalization in deep learning and provide an observation that how model &amp; data complexity influence each other.
Deep Double Descent from Kai-Wen Zhao
]]> 413 0 https://cdn.slidesharecdn.com/ss_thumbnails/ddd-191219042605-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 Recent Object Detection Research & Person Detection /slideshow/recent-object-detection-research-person-detection/198663235 persondetectionpaperreview-191128031815
Introduce recent anchor-free object detection methods on general objects and person detection. The slide summarize more than 10 papers on this topic.]]>
Introduce recent anchor-free object detection methods on general objects and person detection. The slide summarize more than 10 papers on this topic.]]> Thu, 28 Nov 2019 03:18:14 GMT /slideshow/recent-object-detection-research-person-detection/198663235 ssuserb667a8@slideshare.net(ssuserb667a8) Recent Object Detection Research & Person Detection ssuserb667a8 Introduce recent anchor-free object detection methods on general objects and person detection. The slide summarize more than 10 papers on this topic. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/persondetectionpaperreview-191128031815-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Introduce recent anchor-free object detection methods on general objects and person detection. The slide summarize more than 10 papers on this topic.
Recent Object Detection Research & Person Detection from Kai-Wen Zhao
]]> 1046 2 https://cdn.slidesharecdn.com/ss_thumbnails/persondetectionpaperreview-191128031815-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 Learning to discover monte carlo algorithm on spin ice manifold /slideshow/learning-to-discover-monte-carlo-algorithm-on-spin-ice-manifold/132111768 learningtodiscovermontecarloalgorithmonspinicemanifold-190217133702
The global update Monte Carlo sampler can be discovered naturally by trained machine using policy gradient method on topologically constrained environment.]]>
The global update Monte Carlo sampler can be discovered naturally by trained machine using policy gradient method on topologically constrained environment.]]> Sun, 17 Feb 2019 13:37:02 GMT /slideshow/learning-to-discover-monte-carlo-algorithm-on-spin-ice-manifold/132111768 ssuserb667a8@slideshare.net(ssuserb667a8) Learning to discover monte carlo algorithm on spin ice manifold ssuserb667a8 The global update Monte Carlo sampler can be discovered naturally by trained machine using policy gradient method on topologically constrained environment. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/learningtodiscovermontecarloalgorithmonspinicemanifold-190217133702-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> The global update Monte Carlo sampler can be discovered naturally by trained machine using policy gradient method on topologically constrained environment.
Learning to discover monte carlo algorithm on spin ice manifold from Kai-Wen Zhao
]]> 279 3 https://cdn.slidesharecdn.com/ss_thumbnails/learningtodiscovermontecarloalgorithmonspinicemanifold-190217133702-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 Toward Disentanglement through Understand ELBO /slideshow/toward-disentanglement-through-understand-elbo/132111433 disentangle-190217132841
Disentangled representation is the holy grail for representation learning which factorizes human-understandable factors in unsupervised way what help us move forward to interpretable machine learning.]]>
Disentangled representation is the holy grail for representation learning which factorizes human-understandable factors in unsupervised way what help us move forward to interpretable machine learning.]]> Sun, 17 Feb 2019 13:28:41 GMT /slideshow/toward-disentanglement-through-understand-elbo/132111433 ssuserb667a8@slideshare.net(ssuserb667a8) Toward Disentanglement through Understand ELBO ssuserb667a8 Disentangled representation is the holy grail for representation learning which factorizes human-understandable factors in unsupervised way what help us move forward to interpretable machine learning. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/disentangle-190217132841-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Disentangled representation is the holy grail for representation learning which factorizes human-understandable factors in unsupervised way what help us move forward to interpretable machine learning.
Toward Disentanglement through Understand ELBO from Kai-Wen Zhao
]]> 628 1 https://cdn.slidesharecdn.com/ss_thumbnails/disentangle-190217132841-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 Deep Reinforcement Learning: Q-Learning /slideshow/deep-reinforcement-learning-qlearning/106109020 dqn-180716075159
This slide reviews deep reinforcement learning, specially Q-Learning and its variants. We introduce Bellman operator and approximate it with deep neural network. Last but not least, we review the classical paper: DeepMind Atari Game beats human performance. Also, some tips of stabilizing DQN are included.]]>
This slide reviews deep reinforcement learning, specially Q-Learning and its variants. We introduce Bellman operator and approximate it with deep neural network. Last but not least, we review the classical paper: DeepMind Atari Game beats human performance. Also, some tips of stabilizing DQN are included.]]> Mon, 16 Jul 2018 07:51:59 GMT /slideshow/deep-reinforcement-learning-qlearning/106109020 ssuserb667a8@slideshare.net(ssuserb667a8) Deep Reinforcement Learning: Q-Learning ssuserb667a8 This slide reviews deep reinforcement learning, specially Q-Learning and its variants. We introduce Bellman operator and approximate it with deep neural network. Last but not least, we review the classical paper: DeepMind Atari Game beats human performance. Also, some tips of stabilizing DQN are included. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/dqn-180716075159-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> This slide reviews deep reinforcement learning, specially Q-Learning and its variants. We introduce Bellman operator and approximate it with deep neural network. Last but not least, we review the classical paper: DeepMind Atari Game beats human performance. Also, some tips of stabilizing DQN are included.
Deep Reinforcement Learning: Q-Learning from Kai-Wen Zhao
]]> 650 2 https://cdn.slidesharecdn.com/ss_thumbnails/dqn-180716075159-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 Paper Review: An exact mapping between the Variational Renormalization Group and Deep Learning /slideshow/paper-review-an-exact-mapping-between-the-variational-renormalization-group-and-deep-learning/69707050 exact-161201033302
Paper Review on Arxiv article: An exact mapping between the Variational Renormalization Group and Deep Learning]]>
Paper Review on Arxiv article: An exact mapping between the Variational Renormalization Group and Deep Learning]]> Thu, 01 Dec 2016 03:33:02 GMT /slideshow/paper-review-an-exact-mapping-between-the-variational-renormalization-group-and-deep-learning/69707050 ssuserb667a8@slideshare.net(ssuserb667a8) Paper Review: An exact mapping between the Variational Renormalization Group and Deep Learning ssuserb667a8 Paper Review on Arxiv article: An exact mapping between the Variational Renormalization Group and Deep Learning <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/exact-161201033302-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Paper Review on Arxiv article: An exact mapping between the Variational Renormalization Group and Deep Learning
Paper Review: An exact mapping between the Variational Renormalization Group and Deep Learning from Kai-Wen Zhao
]]> 935 5 https://cdn.slidesharecdn.com/ss_thumbnails/exact-161201033302-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 NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accelerated Gradient Method /slideshow/nag-theory-48129263/48129263 nagtheory-150514040517-lva1-app6891
Paper review and presentation of the NIPS 2014 paper which talking about modeling the gradient descent method using ODE.]]>
Paper review and presentation of the NIPS 2014 paper which talking about modeling the gradient descent method using ODE.]]> Thu, 14 May 2015 04:05:17 GMT /slideshow/nag-theory-48129263/48129263 ssuserb667a8@slideshare.net(ssuserb667a8) NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accelerated Gradient Method ssuserb667a8 Paper review and presentation of the NIPS 2014 paper which talking about modeling the gradient descent method using ODE. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/nagtheory-150514040517-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Paper review and presentation of the NIPS 2014 paper which talking about modeling the gradient descent method using ODE.
NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accelerated Gradient Method from Kai-Wen Zhao
]]> 1317 5 https://cdn.slidesharecdn.com/ss_thumbnails/nagtheory-150514040517-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 High Dimensional Data Visualization using t-SNE /slideshow/visualization-data-using-tsne/40946612 tsne-141030223547-conversion-gate02
Review of the t-SNE algorithm which helps visualizing the high dimensional data on manifold by projecting them onto 2D or 3D space with metric preserving.]]>
Review of the t-SNE algorithm which helps visualizing the high dimensional data on manifold by projecting them onto 2D or 3D space with metric preserving.]]> Thu, 30 Oct 2014 22:35:47 GMT /slideshow/visualization-data-using-tsne/40946612 ssuserb667a8@slideshare.net(ssuserb667a8) High Dimensional Data Visualization using t-SNE ssuserb667a8 Review of the t-SNE algorithm which helps visualizing the high dimensional data on manifold by projecting them onto 2D or 3D space with metric preserving. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/tsne-141030223547-conversion-gate02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Review of the t-SNE algorithm which helps visualizing the high dimensional data on manifold by projecting them onto 2D or 3D space with metric preserving.
High Dimensional Data Visualization using t-SNE from Kai-Wen Zhao
]]> 7218 6 https://cdn.slidesharecdn.com/ss_thumbnails/tsne-141030223547-conversion-gate02-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 https://cdn.slidesharecdn.com/profile-photo-ssuserb667a8-48x48.jpg?cb=1634049336 https://cdn.slidesharecdn.com/ss_thumbnails/learningvisualrepresentationwithouthuman-label-200305055852-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/learning-visual-representation-without-human-label/229715973 Learning visual repres... https://cdn.slidesharecdn.com/ss_thumbnails/ddd-191219042605-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/deep-double-descent/207536470 Deep Double Descent https://cdn.slidesharecdn.com/ss_thumbnails/persondetectionpaperreview-191128031815-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/recent-object-detection-research-person-detection/198663235 Recent Object Detectio...