Uploaded bydrift9999
3,107 views

Neural Network Classification-Explanation

This document summarizes how a basic neural network processes an input image to produce an output classification. It shows how the input is normalized and sent to the hidden layer, where each node calculates a weighted sum of its inputs and determines its activation. The hidden layer outputs are then sent to the output layer, where each node again calculates a weighted sum and activation to determine the final classification. The goal is for only one output node to activate, correctly identifying the input digit.

Embed presentation

1. To convert the input into something that the network can process, we normalise the size of the input and convert it to an array of pixels (here a 10 x 13 array).
HIDDEN LAYER INPUT OUTPUT LAYER LAYER 1 -1 … … -1 … 2. Inputs are sent into the network, possibly ‘1’ for a dark pixel and ‘-1’ for a light pixel.
HIDDEN LAYER INPUT OUTPUT LAYER LAYER 1 1 -1 -1 … … -1 -1 … 3. Each node in the hidden layer evaluates a weighted sum of its inputs, and determines its state. We will demonstrate this for 1 node.
HIDDEN LAYER INPUT OUTPUT LAYER LAYER 1 1 -1 -1 … … -1 -1 … 4. Let this hidden node be j, and nodes connecting to it be i. We find w ij x j all i
HIDDEN LAYER INPUT OUTPUT LAYER .4 LAYER 1 .2 1 .7 -1 -1 … … -1 -1 … There are 26 input nodes; suppose we determine that w ij x j (0.4 1) (0.2 1) ... (0.7 1) 0.3 all i
HIDDEN LAYER INPUT OUTPUT LAYER .4 LAYER 1 .2 1 .7 -1 -1 … … -1 -1 … 5. We then decide based on this sum how to determine the state of this node. A possible rule would be that if the sum is nonnegative, the state should be 1 (the neuron fires), and if it is negative, the state should be -1 (it doesn’t).
HIDDEN LAYER INPUT -1 OUTPUT LAYER .4 LAYER 1 .2 1 .7 -1 -1 … … -1 -1 … Thus, as –0.3 < 0, this node’s state is set to –1.
HIDDEN LAYER INPUT -1 OUTPUT LAYER LAYER 1 1 1 -1 -1 1 … … -1 -1 -1 … -1 6. We repeat this process for every other node in the hidden layer.
HIDDEN LAYER INPUT -1 OUTPUT LAYER .3 LAYER 1 1 .4 1 1 1 .4 -1 -1 1 .1 … … .2 -1 -1 -1 … -1 7. With all of the states in the hidden layer computed, we begin to compute the states of the output layer in the same way. Here, suppose w ij x j 0.2 0, so we set the node's state to 1. all i
HIDDEN LAYER INPUT -1 OUTPUT LAYER LAYER 1 1 1 1 1 -1 -1 1 -1 -1 … … -1 -1 -1 -1 -1 … -1 8. Repeat for every node in the output layer. We now have our set of outputs. Each node in the output layer would correspond to 1 digit.
HIDDEN 1 LAYER INPUT -1 OUTPUT LAYER LAYER 1 1 1 1 1 -1 -1 1 -1 -1 … … -1 -1 -1 -1 -1 … -1 9. Hopefully, we have only one output node firing; this means that the network has identified the input to be the digit corresponding to that output. If none / more than one fire, the network has not successfully determined what digit was input.

More Related Content

PPTX
Artificial neural network
byDEEPASHRI HK
 
PPTX
Stabilization of TORA System: A Backstepping Based Hierarchical Sliding Mode ...
byShubhobrata Rudra
 
PPTX
Neural network & its applications
byAhmed_hashmi
 
PDF
Network Identification via Node Knock-out
byMarzieh Nabi
 
PDF
The Back Propagation Learning Algorithm
byESCOM
 
PDF
Applying your Convolutional Neural Networks
byDatabricks
 
PDF
A graphic library and an application for simple curve manipolation
bygraphitech
 
PDF
Stanford ml neuralnetwork
byShigekazu Takei
 
Artificial neural network
byDEEPASHRI HK
 
Stabilization of TORA System: A Backstepping Based Hierarchical Sliding Mode ...
byShubhobrata Rudra
 
Neural network & its applications
byAhmed_hashmi
 
Network Identification via Node Knock-out
byMarzieh Nabi
 
The Back Propagation Learning Algorithm
byESCOM
 
Applying your Convolutional Neural Networks
byDatabricks
 
A graphic library and an application for simple curve manipolation
bygraphitech
 
Stanford ml neuralnetwork
byShigekazu Takei
 

Similar to Neural Network Classification-Explanation

PPT
Neural network and mlp
bypartha pratim deb
 
PDF
Hands-on MapReduce Programming
byOrzota
 
PPTX
Neural network
bySilicon
 
PPTX
Computer graphics
byNanhen Verma
 
PPT
Ann ics320 part4
byHasan Suthar
 
PPTX
Cg
byAmit Pathak
 
PDF
Chebyshev Functional Link Artificial Neural Networks for Denoising of Image C...
byIDES Editor
 
PDF
Computer Graphics - Output Primitive
byRupesh Mishra
 
PPT
Shape drawing algs
byMusawarNice
 
PPTX
Derby presentation
byScott Turner
 
PPT
Circuitanlys2
bySenthil Kumar
 
PDF
Lecture 2: Artificial Neural Network
byMohamed Loey
 
PPT
Lect25 Engin112
byJohn Williams
 
Neural network and mlp
bypartha pratim deb
 
Hands-on MapReduce Programming
byOrzota
 
Neural network
bySilicon
 
Computer graphics
byNanhen Verma
 
Ann ics320 part4
byHasan Suthar
 
Cg
byAmit Pathak
 
Chebyshev Functional Link Artificial Neural Networks for Denoising of Image C...
byIDES Editor
 
Computer Graphics - Output Primitive
byRupesh Mishra
 
Shape drawing algs
byMusawarNice
 
Derby presentation
byScott Turner
 
Circuitanlys2
bySenthil Kumar
 
Lecture 2: Artificial Neural Network
byMohamed Loey
 
Lect25 Engin112
byJohn Williams
 

Neural Network Classification-Explanation

  • 1.
    1. To convertthe input into something that the network can process, we normalise the size of the input and convert it to an array of pixels (here a 10 x 13 array).
  • 2.
    HIDDEN LAYER INPUT OUTPUT LAYER LAYER 1 -1 … … -1 … 2. Inputs are sent into the network, possibly ‘1’ for a dark pixel and ‘-1’ for a light pixel.
  • 3.
    HIDDEN LAYER INPUT OUTPUT LAYER LAYER 1 1 -1 -1 … … -1 -1 … 3. Each node in the hidden layer evaluates a weighted sum of its inputs, and determines its state. We will demonstrate this for 1 node.
  • 4.
    HIDDEN LAYER INPUT OUTPUT LAYER LAYER 1 1 -1 -1 … … -1 -1 … 4. Let this hidden node be j, and nodes connecting to it be i. We find w ij x j all i
  • 5.
    HIDDEN LAYER INPUT OUTPUT LAYER .4 LAYER 1 .2 1 .7 -1 -1 … … -1 -1 … There are 26 input nodes; suppose we determine that w ij x j (0.4 1) (0.2 1) ... (0.7 1) 0.3 all i
  • 6.
    HIDDEN LAYER INPUT OUTPUT LAYER .4 LAYER 1 .2 1 .7 -1 -1 … … -1 -1 … 5. We then decide based on this sum how to determine the state of this node. A possible rule would be that if the sum is nonnegative, the state should be 1 (the neuron fires), and if it is negative, the state should be -1 (it doesn’t).
  • 7.
    HIDDEN LAYER INPUT -1 OUTPUT LAYER .4 LAYER 1 .2 1 .7 -1 -1 … … -1 -1 … Thus, as –0.3 < 0, this node’s state is set to –1.
  • 8.
    HIDDEN LAYER INPUT -1 OUTPUT LAYER LAYER 1 1 1 -1 -1 1 … … -1 -1 -1 … -1 6. We repeat this process for every other node in the hidden layer.
  • 9.
    HIDDEN LAYER INPUT -1 OUTPUT LAYER .3 LAYER 1 1 .4 1 1 1 .4 -1 -1 1 .1 … … .2 -1 -1 -1 … -1 7. With all of the states in the hidden layer computed, we begin to compute the states of the output layer in the same way. Here, suppose w ij x j 0.2 0, so we set the node's state to 1. all i
  • 10.
    HIDDEN LAYER INPUT -1 OUTPUT LAYER LAYER 1 1 1 1 1 -1 -1 1 -1 -1 … … -1 -1 -1 -1 -1 … -1 8. Repeat for every node in the output layer. We now have our set of outputs. Each node in the output layer would correspond to 1 digit.
  • 11.
    HIDDEN 1 LAYER INPUT -1 OUTPUT LAYER LAYER 1 1 1 1 1 -1 -1 1 -1 -1 … … -1 -1 -1 -1 -1 … -1 9. Hopefully, we have only one output node firing; this means that the network has identified the input to be the digit corresponding to that output. If none / more than one fire, the network has not successfully determined what digit was input.