Differences

This shows you the differences between two versions of the page.

--- projects:hope:start [2015/02/11 01:53] – created hj
+++ projects:hope:start [2016/04/25 14:55] (current) – hj
@@ Line 1: / Line 1: @@
-====== Current Projects ======
+====== HOPE ======
 ===== Hybrid Orthogonal Projection & Estimation (HOPE) =====
 {{:projects:current:one-nn-layer.png?0x220 |NN hidden layer}}{{ :projects:current:one-hope-layer.png?0x220| HOPE}}
-Each hidden layer in neural networks can be formulated as one HOPE model[1]
 \\
-  * The HOPE model combines a linear orthogonal projection and a mixture model under a unied generative modelling framework;
+Each hidden layer in neural networks can be formulated as one HOPE model [1]
-  * The HOPE model can be used as a novel tool to probe why and how NNs work;
-  * The HOPE model provides several new learning algorithms to learn NNs either supervisedly or unsupervisedly.
 \\
+  * The HOPE model combines a linear orthogonal projection and a mixture model under a unified generative modelling framework;
+  * The HOPE model can be used as a novel tool to probe why and how NNs work;
+  * The HOPE model provides several new learning algorithms to learn NNs in either supervised or unsupervised ways.
 **Reference:**
 \\
 [1] //Shiliang Zhang and Hui Jiang//, "Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks," [[http://arxiv.org/abs/1502.00702|arXiv:1502.00702]].
+[2] //Shiliang Zhang, Hui Jiang, Lirong Dai//, "The New HOPE Way to Learn Neural Networks", Proc. of Deep Learning Workshop at ICML 2015, July 2015. ([[https://8109f4a4-a-62cb3a1a-s-sites.googlegroups.com/site/deeplearning2015/9.pdf?attachauth=ANoY7coK1o0yBn1dsWEI0HgzM8TRfaBZAVw5BlivHyIiOJt3Hz1Q-fSv3qKwTo4eeS2bdcIrseorD-GCFaggMP9n6EKExhoYnm8smj5LogA6kmlM5SPmMWJxf3uhMRKk5T0M9_cEdtCVwCBSQh4Ya3PYW5OogwFzibs-vpFIZfN6OQG50CmwNBK4x3-tyi0nrihKfNFeMMbUyMWZeeSj9ToElpkc2qB17A%3D%3D&attredirects=0|paper]])
+[3] //S. Zhang, H. Jiang, L. Dai//, “[[http://jmlr.org/papers/v17/15-335.html| Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Learn Neural Networks]],” //Journal of Machine Learning Research (JMLR)//, 17(37):1−33, 2016.
 **Software:**
 \\
-The matlab codes to reproduce the MNIST results in [1] can be downloaded here.
+The matlab codes to reproduce the MNIST results in [1,2] can be downloaded {{:projects:hope:hope4mnist_matlab.rar|here}}.
+<HTML>
+<script>
+  (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
+  (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
+  m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
+  })(window,document,'script','//www.google-analytics.com/analytics.js','ga');
+  ga('create', 'UA-59662420-1', 'auto');
+  ga('send', 'pageview');
+</script>
+</HTML>