Feedforward neural network
Download as PPTX, PDF8 likes12,249 views
This slide is prepared for the lectures-in-turn challenge within the study group of social informatics, kyoto university.
Ad
More Related Content
What's hot (20)
Similar to Feedforward neural network (20)
Ad
Recently uploaded (20)
Ad
Feedforward neural network
- 1. YONG Sopheaktra M1 Yoshikawa-Ma Laboratory 2015/07/26 Feedforward neural networks 1 (multilayer perceptrons)
- 2. Kyoto University • Artificial Neural Network • Perceptron Algorithm • Multi-layer perceptron (MLP) • Overfitting & Regularization Content 2
- 3. Kyoto University • An Artificial Neural Network (ANN) is a system that is based on biological neural network (brain). ▫ The brain has approximately 100 billion neurons, which communicate through electro-chemical signals ▫ Each neuron receives thousands of connections (signals) ▫ If the resulting sum of signals surpasses certain threshold, the response is sent • The ANN attempts to recreate the computational mirror of the biological neural network … Artificial Neural Network 3
- 5. Kyoto University What is Perceptron? 5 • A perceptron models a neuron • It receives n inputs (feature vector) • It sum those inputs , calculated, then output • Used for linear or binary classification
- 6. Kyoto University 6 Perceptron • The perceptron consists of weights, the summation processor, and an activation function • A perceptron takes a weighted sum of inputs and outputs:
- 7. Kyoto University Weight & Bias 7 • Bias can also be treated as another input ▫ The bias allow to shift the line • The weights determine the slope
- 8. Kyoto University Transfer or Activation Functions 8 • The transfer function translate the input signals to output signals • It uses a threshold to produce an output • Some examples are ▫ Unit Step (threshold) ▫ Sigmoid (logistic regression) ▫ Piecewise linear ▫ Gaussian
- 9. Kyoto University 9 Unit Step (Threshold) • The output is set depending on whether the total input is greater or less than some threshold value.
- 10. Kyoto University 10 Piecewise Linear • The output is proportional to the total weighted output.
- 11. Kyoto University 11 Sigmoid function • It is used when the output is expected to be a positive number ▫ It generates outputs between 0 and 1
- 12. Kyoto University 12 Gaussian • Gaussian functions are bell-shaped curves that are continuous • It is used in radial basis function ANN (RBF kernel – Chapter 14) ▫ Output is real value
- 13. Kyoto University 13 The learning rate • To update the weights and bias to get smaller error • Help us control how much we change the weight and bias
- 14. Kyoto University 14 How the algorithm work? • Initialize the weights (zero or small random value) • Pick a learning rate (0 – 1) • For each training set • Compute the activation output ▫ Adjusting Error = differences between predicted and actual Update bias and weight • Repeating till the error is very small or zero • If the it is linear separable, we will found solution
- 16. Kyoto University 16 What if the data is non-linearly separable? • Because SLP is a linear classifier and if the data are not linearly separable, the learning process will never find the solution • For example: XOR problem
- 18. Kyoto University 18 XOR Classification (Xor_classification.zip)
- 19. Kyoto University 19 • A series of logistic regression models stacked on top of each other, with the final layer being either another logistic regression or a linear regression model, depending on whether we are solving a classification or regression problem. Multi-layer perceptron (MLP)
- 21. Kyoto University 21 A closer look
- 23. Kyoto University 23 • Use output error, to adjust the weights of inputs at the output layer • Calculate the error at the previous layer and use it to adjust the weights • Repeat this process of back-propagating errors through any number of layers • You may find mathematical equation of how to minimize cost function of neural network at 16.5.4 The backpropagation algorithm The Back Propagation Algorithm
- 24. Kyoto University 24 Convolutional neural networks http://yann.lecun.com/exdb/lenet/index.html • Designed to recognize visual patterns directly from pixel images with minimal preprocessing. • The purpose of multiple hidden units are used to learn non-linear combination of the original inputs (feature extraction) ▫ Individual Informative ▫ Each pixel in an image is not very informative ▫ But the combination will tell
- 28. Kyoto University 28 Overfitting Problem
- 29. Kyoto University 29 Cross validation error
- 30. Kyoto University 30 • Simplifier the parameters/features ▫ Remove some unnecessary features • Regularization ▫ Adjusting the weight How to address it?
- 31. Kyoto University 31 • The MLP can overfit, esp. if the number of nodes is large • A simple way to prevent is early stopping ▫ Stopping the training procedure when the error on the validation set first start to increase • Techniques are ▫ Consistent Gaussian prior ▫ Weight pruning: smaller the parameters value ▫ Soft weight sharing: group of parameters value have similar value ▫ Semi-supervised embedding: used with deep learning NN ▫ Bayesian Inference Determine number of hidden units – faster than cross-validation Regularization
- 32. Kyoto University 32 Thanks You
- 33. Kyoto University • https://www.coursera.org/learn/machine-learning • https://www.youtube.com/playlist?list=PLea0WJq13cnCS4LLMeUuZmTx qsqlhwUoe • http://yann.lecun.com/exdb/lenet/index.html Reference 33
Editor's Notes
- #5: Dendrite: input Axon: output