Title: Convolutional%20Deep%20Belief%20Networks%20for%20Scalable%20Unsupervised%20Learning%20of%20Hierarchical%20Representations%20%20Honglak%20Lee,%20Roger%20Grosse,%20Rajesh%20Ranganath,%20and%20Andrew%20Y.%20Ng%20ICML%202009
1Convolutional Deep Belief Networks for Scalable
Unsupervised Learning of Hierarchical
Representations Honglak Lee, Roger Grosse,
Rajesh Ranganath, and Andrew Y. Ng ICML 2009
- Presented by Mingyuan Zhou
- Duke University, ECE
- September 18, 2009
2Outline
- Motivations
- Contributions
- Backgrounds
- Algorithms
- Experiment results
- Deep Vs Shallow
- Conclusions
3Motivations
- To Learn hierarchical models which simultaneously
represent multiple levels, e.g., pixel
intensities, edges, object parts, objects, and
beyond can be represented by layers from low to
high. - Combining top-down and bottom-up processing of an
image. - Limitations of deep belief networks (DBNs)
- Scaling DBNs to realistic-size images remains
challenging images are high-dimentional and
objects can appear at arbitrary locations in
images.
4Contributions
- Convolutional RBM feature detectors are shared
among all locations in an image. - Probabilistic max-pooling in a probabilistic
sound way allowing higher-layer units to cover
larger areas of the input. - The first translation invariant hierarchical
generative model supporting both top-down and
bottom-up probabilistic inference and sales to
realistic image sizes.
5Backgrounds Restricted Boltzmann Machine (RBM)
(binary v)
(real-value v)
- Giving the visible layer, the hidden units are
conditionally independent, and vise versa. - Efficient block Gibbs sampling can be performed
by alternately sampling each layers units. - Computing the exact gradient of the
log-likelihood is intractable, so the contrastive
divergence approximation is commonly used.
6Backgrounds Deep belief network (DBN)
- In a DBN, two adjacent layers have a full set of
connections between them, but no two units in the
same layer are connected. - A DBN can be formed by stacking RBMs.
- An efficient algorithm for training DBNs (Hinton
et al., 2006) greedily training each layer,
from lowest to highest, as an RBM using the
previous layer's activations as inputs.
7Algorithms Convolutional RBM (CRBM)
8Algorithms Probabilistic max-pooling
9Algorithms Probabilistic max-pooling
- Each unit in a pooling layer computes the maximum
activation of the units in a small region of the
detection layer. - Shrinking the representation with max-pooling
allows higher-layer representations to be
invariant to small translations of the input and
reduces the computational burden. - Max-pooling was intended only for feed-forward
architectures. A generative model of images which
supports both top-down and bottom-up inference is
of interest.
10Algorithms Sparsity regulations
- Only a tiny fraction of the units should be
active in relation to a given stimulus. - Regularizing the objective function to encourage
each of the hidden units to have a mean
activation close to some small constant .
11Algorithms Convolutional DBN (CDBN)
- CDBN consists of several max-pooling-CRBMs
stacked on top of one another. - Once a given layer is trained, its weights are
frozen, and its activations are used as input to
the next layer.
12Hierarchical probabilistic inference
13Experimental Results natural images
14Experimental Results image classification
15Experimental Results unsupervised learning of
object parts
16Experimental Results Hierarchical probabilistic
inference
17Deep Vs Shallow
.
- From Jason Westons slides DEEP LEARNING VIA
SEMI-SUPERVISED EMBEDDING, ICML 2009 WORKSHOP ON
LEARNING FEATURE HIERARCHIES
From Francis Bachs slides Convex sparse
methods for feature hierarchies, ICML 2009
WORKSHOP ON LEARNING FEATURE HIERARCHIES
18Conclusions
- Convolutional deep belief network
- A scalable generative model for learning
hierarchical representations from unlabeled
images. - Performing well in a variety of visual
recognition tasks.