Download presentation
Presentation is loading. Please wait.
Published byKelly Dickerson Modified over 9 years ago
2
Neural Network and Deep Learning 王强昌 2015-11-24 MLA lab
3
Neural Network and Deep Learning Artificial Neural Network Why we go deep? Amazing achievement Deep learning-getting started
4
Artificial Neural Network How do ANNs work? Feed-forward process About Weights Gradient Descent Back-propagation process Summaries
5
Artificial Neural Network (ANN) is a technique for solving problems by constructing software that works like our brains.
6
Our brains are a huge network of processing elements. A typical brain contains a network of 10 billion neurons.
7
An artificial neuron is an imitation of a human neuron
8
Now, let us have a look at the model of an artificial neuron.
9
Transfer Function (Activation Function) Output x1x1 x2x2 xmxm ∑ y Neuron Input w1w1 w2w2 wmwm Weights...... f(v k ).....
10
An example Sum : (1 0.25) + (0.5 (-1.5)) = 0.25 + (-0.75) = - 0.5 Transfer function : if we get then
11
Transfer (Activation, Squash) function: Limits node output; enhances Non-linearity. For the function below, we limit the output in the range [0,1]. An example:
12
Artificial Neural Network How do ANNs work? Feed-forward process About Weights Gradient Descent Back-propagation process Summaries
13
Feed-forward process Information flow is unidirectional Data is presented to input layer Data example Pixel intensity (for image classification). Share prices (for stock market prediction ). Passed on to hidden Layer Passed on to output layer Hidden layer: internal representation (interpretation) of data. Layer
14
Picture below illustrates how data is propagated through the network. w (xm)n represent weights of connections between network input x m and neuron n in next layer. y n represents output of neuron n. Input layerHidden layer Output layer
15
Input layerHidden layer Output layer
16
Propagation of data through the hidden layer. w mn represent weights of connections between neuron m and neuron n in the next layer. Output layer Hidden layer Input layer
17
Propagation of data through the output layer. Input layerHidden layer Output layer
18
Artificial Neural Network How do ANNs work? Feed-forward process About Weights Gradient Descent Back-propagation process Summaries
19
About Weights Weights w settings determine the behaviour of a network How can we find the right weights ?
20
Example: Voice Recognition Task: Learn to discriminate between two different voices saying “Hello” Data Sources Steve David Input data Frequency distribution (60 bins)
21
Network architecture Feed forward network (predefined) 60 input units (one for every frequency bin) 6 hidden units 2 output units (0-1 for “Steve”, 1-0 for “David”)
22
Presenting the data Steve David
23
Presenting the data (untrained network) Steve 0.43 0.57 David 0.7 0.3
24
Calculate error (suppose the error function is absolute value function) Steve:0-1 |0.43 – 0| = 0.43 |0.57 – 1| = 0.43 David:1-0 |0.7 – 1| = 0.3 |0.3 – 0| = 0.3
25
Backprop error and adjust weights (just the last hidden layer) Steve |0.43 – 0| = 0.43 |0.57 – 1| = 0.43 David |0.7 – 1| = 0.3 |0.3 – 0| = 0.3 How do we adjust the weights ? weights
26
Artificial Neural Network How do ANNs work? Feed-forward process About Weights Gradient Descent Back-propagation process Summaries
27
Gradient Descent Think of (w 0,w 1,…,w n-1 ) as a point in an n-dimensional space. Suppose the error function is E(w 0,w 1,…,w n-1 ). Try to minimize error E(w 0,w 1,…,w n-1 ) by changing the point position on the “error surface”.
28
How do we change w i ? Change i-th weight by η w i = η* : direction of going down. η: length of going down, a constant. w i (new)=w i (old)+ w i
29
Repeat the procedure above, we can finally get the minimum. But we need to compute derivative first ! Grad E =[,, …, ]
30
Artificial Neural Network How do ANNs work? Feed-forward process About Weights Gradient Descent Back-propagation process Summaries
31
Back-propagation process the output of the network y is compared with the desired output z (the target), compute the error, suppose we get error function
32
The idea is to propagate error back to all neurons. The weights' coefficients w mn used to propagate errors back are equal to this used during feed-forward process. The direction of data flow is changed (signals are propagated from output to inputs one after the other). depends on what function f(e) is. if f(e)=e, then 链式求导 w 56
33
If propagated errors came from few neurons they are added. The illustration is below: w 46 链式求导 depends on what function f(e) is. if f(e)=e, then w 24 w 34
34
Continue to propagate the error, we can modify the weights for the inputs nodes:
35
Artificial Neural Network How do ANNs work? Feed-forward process About Weights Gradient Descent Back-propagation process Summaries
36
Summaries 1. Initialize network with random weights. 2. For all training cases, repeat: a. Feed-forward process: present training inputs to network and calculate output. b. b. Back-propagation process: for all layers (starting with output layer, back to input layer): Computes the error term for the output units using the observed error. From output layer, repeat - propagating the error term back to the previous layer - updating the weights between the two layers until the earliest hidden layer is reached.
37
Neural Network and Deep Learning Artificial Neural Network Why we go deep? Amazing achievement Deep learning-getting started
38
Why we go deep? Learning multiple levels of representation
39
Learning Non-Linear Features
41
Learning features, not just handcrafting them. Most ML systems use very carefully hand-designed features and representations. So, many practitioners are very experienced – and good at such feature design (or kernel design). Hand-crafting features are brittle, incomplete.
42
Highly varying functions can be efficiently represented with deep architectures. Problems which can be represented with a polynomial number of nodes with k layers, may require an exponential number of nodes with k-1 layers.
43
Neural Network and Deep Learning Artificial Neural Network Why we go deep? Amazing achievement Deep learning-getting started
44
Amazing achievement on ImageNet classification Database: part of ImageNet database, 1000 categories, 1.2 million training images, 150,000 testing images. Task: classify testing image into one of 1000 categories. Examples of two categories needed to be differentiated: Differentiate 波斯猫 布偶猫
45
Machine is as good as human !!! A New Era Begins: Deep Convolutional Neural Network (DCNN)
46
Neural Network and Deep Learning Artificial Neural Network Why we go deep? Amazing achievement Deep learning-getting started
47
Deep learning-getting started http://blog.csdn.net/zouxy09/article/details/8775360 http://blog.csdn.net/zouxy09/article/details/8775360 了解一些 deep learning 基本方法的思想 http://ufldl.stanford.edu/wiki/index.php/UFLDL 教程 deep learning 大牛 Andrew Ng 所写 ,还 有 实验、 源代 码, 推 荐 细读
48
Thank You!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.