Differences

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

--- projects:current:start [2015/02/11 01:39] – hj
+++ projects:current:start [2015/02/11 01:51] (current) – hj
@@ Line 2: / Line 2: @@
-===== Current Projects =====
+===== Hybrid Orthogonal Projection & Estimation (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;
+  * 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.
+\\
+**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]].
-{{{:projects:current:one-nn-layer.png?0x200 |NN hidden layer}}{{ :projects:current:one-hope-layer.png?0x200| HOPE}}}
+**Software:**
+\\
+The matlab codes to reproduce the MNIST results in [1] can be downloaded here.
-Each hidden layer in neural networks can be formulated as one HOPE model