Observable
Data
Model Information
Observable
Data
Model Information
Speech
Recognition
I am a boy
Observable
Data
Model Information
Image
Classify
Cat
Observable
Data
Model Information
HOW?
• Core visual object recognition
Feedback
• Weakness in kernel machine(SVM …):
• It does not scale well with sample size.
• Based on matching local templates.
• the training data is referenced for test data
• Local representation VS distributed representation
• N N(Neural Network) -> Kernel machine -> Deep NN
• Deep learning is all about deep neural networks
• 1949 : Hebbian learning
• Donald Hebb : the father of neural networks
• 1958 : (single layer) Perceptron
• Frank Rosenblatt
- Marvin Minsky, 1969
• 1986 : Multilayer Perceptron(Back propagation)
• David Rumelhart, Geoffrey Hinton, and Ronald Williams
• 2006 : Deep Neural Networks
• Geoffrey Hinton and Ruslan Salakhutdinov
Hand-
Crafted
Features
Trainable
Generic
Classifier
F(X;𝜃)
𝜃
Simple
Classifier
Layer
1
Simple
Classifier
Layer
2
Layer
N
Layer
1
Simple
Classifier
Layer
2
Layer
N
Layer
1
Simple
Classifier
Layer
2
Layer
N
Layer
1
Simple
Classifier
Layer
2
Layer
N
Layer
1
Simple
Classifier
Layer
2
Layer
N
Trainable
Generic
Classifier
Hand-
crafted
Features
Layer
1
Simple
Classifier
Layer
2
Layer
N
Trainable
Generic
Classifier
Hand-
crafted
Features
Layer
1
Simple
Classifier
Layer
2
Layer
N
Shallow learning Deep learning
feature extraction by domain experts
(SIFT, SURF, orb...)
automatic feature extraction from data
separate modules
(feature extractor + trainable classifier)
unified model : end-to-end learning
(trainable feature + trainable classifier)
i j
• http://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html
• convolutional neural networks (popular): LeCun
• Alex Krizhevsky: Hinton (python, C++)
• https://code.google.com/p/cuda-convnet/
• Caffe: UC Berkeley (C++)
• http://caffe.berkeleyvision.org/
머신러닝 시그 세미나_(deep learning for visual recognition)
머신러닝 시그 세미나_(deep learning for visual recognition)

머신러닝 시그 세미나_(deep learning for visual recognition)