Artificial Neural Network(Artificial intelligence)

Artificial Neural Network(Artificial intelligence)

• 1.
  Artificial Neural Network Preparedby- Md. Mahmudul Hasan Lecturer, Department of CSE Pabna University of Science and Technology, Pabna
• 2.
  Neural Network • Neuron •Network Definition
• 3.
  Data Processing ofa Neuron • Propagation Function
• 4.
  Data Processing ofa Neuron (Cont..) • Activation Function
• 5.
  Data Processing ofa Neuron (Cont..) • Output Function
• 6.
  Learning and TrainingSamples • Developing new connections, • Deleting existing connections, • Changing connecting weights, • Changing the threshold values of neurons, • Varying one or more of the three neuron • Developing new neurons, • Deleting existing neurons
• 7.
  Learning and TrainingSamples (Cont..) • Unsupervised Learning ▫ Training set consists of input patterns ▫ Network tries by itself to detect similarities and generate pattern classes. • Supervised Learning ▫ Training set consists of input patterns with correct results. ▫ Network can receive a precise error vector can be returned. ▫ Steps: Entering, Forward Propagation, Comparing, Corrections of the network, Corrections applied.
• 8.
  Perceptron and Backpropagation • Perceptron ▫ network containing a retina that is used only for data acquisition. ▫ has fixed-weighted connections with the first neuron layer (input layer). ▫ followed by at least one trainable weight layer ▫ One neuron layer is completely linked with the following layer.
• 9.
  Perceptro (Cont..)
• 10.
  Perceptro (Cont..)
• 11.
  Backpropagation
• 12.
  Hopefield Network • Neuronsbias each other • Key Properties • Significance of Weight • Learning procedure by codebook vectors