1 / 18

Question

Question. Although we have only a rudimentary understanding of biological neural networks, is it possible to construct a small set of simple artificial “ neurons ” and perhaps train them to serve a useful function? The answer is “ yes .” Architecture ? Learning Rule ?. Architecture.

monet
Download Presentation

Question

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Question Although we have only a rudimentary understandingof biological neural networks, is it possible to construct a small set ofsimple artificial “neurons” and perhaps train them to serve a useful function? The answer is “yes.” Architecture ? Learning Rule ?

  2. Architecture

  3. Architecture

  4. Architecture

  5. Architecture

  6. Learning Rule,Biological Inspiration Learning is viewed as the establishment of new connectionsbetween neurons or the modification of existing connections. Neural structures continue to change throughout life. These later changes tend to consist mainly of strengthening orweakening of synaptic junctions. For instance, it is believed that new memories are formed by modification of these synaptic strengths. Thus, the process of learning a new friend’s face consists of altering various synapses.

  7. Learning Rule,ANN Learning is viewed as the establishment of new connectionsbetween neurons or the modification of existing connections. learning rule is defined as a procedure for modifying the weights and biases of a network. This procedure may also be referred to as a training algorithm

  8. Learning Rules Categories In supervised learning, the learning rule is provided with a set of examples (thetraining set) of proper network behavior Where pq is an input to the network, and tqis the corresponding correct(target) output. In unsupervised learning, the weights and biases are modified in response tonetwork inputs only. There are no target outputs available. Most of thesealgorithms perform clustering operations. They categorize the input patternsinto a finite number of classes.

  9. Perceptrons The perceptron was created by Rosenblatt. Single-layer network whose weights and biases could be trainedto produce a correcttarget vector when presented with the corresponding input vector. Perceptron Architecture ? Perceptron Learning Rule ?

  10. Perceptron Neuron The perceptron neuron produces a 1 if the net input into the transfer function is equal to or greater than 0; otherwise it produces a 0.

  11. Perceptron Architecture Perceptron Architecture

  12. Perceptron Learning Rule (learnp) CASE 1. If an input vector is presented and the output of the neuron is correct(a = t, and e = t – a = 0), then the weight vector w is not altered. CASE 2. If the neuron output is 0 and should have been 1 (a = 0 and t = 1, ande = t – a = 1), the input vector p is added to the weight vector w. CASE 3. If the neuron output is 1 and should have been 0 (a = 1and t = 0, and e= t – a = –1), the input vector p is subtracted from the weight vector w.

  13. Perceptron Learning Rule (learnp) CASE 1. If an input vector is presented and the output of the neuron is correct(a = t, and e = t – a = 0), then the weight vector w is not altered. CASE 1. If e = 0, then make a change Δw equal to 0. CASE 2. If the neuron output is 0 and should have been 1 (a = 0 and t = 1, ande = t – a = 1), the input vector p is added to the weight vector w. CASE 2. If e = 1, then make a change Δw equal to pT. CASE 3. If the neuron output is 1 and should have been 0 (a = 1and t = 0, and e= t – a = –1), the input vector p is subtracted from the weight vector w. CASE 3. If e = –1, then make a change Δw equal to –pT.

  14. Perceptron Learning Rule (learnp) CASE 1. If e = 0, then make a change Δw equal to 0. CASE 2. If e = 1, then make a change Δw equal to pT. CASE 3. If e = –1, then make a change Δw equal to –pT. All three cases can then be written with a single expression Δw = (t – a)pT = epT

  15. Perceptron Learning Rule (learnp) The Perceptron Learning Rule can be summarized as follows Wnew = Wold + epT bnew = bold +e wheree = t – a

  16. Perceptron Learning Rule (learnp) >> net = newp([-1 1;-2 +2],1); >> p =[1 -1 0; 2 2 -2]; >> t =[0 1 1]; >> net = train(net,p,t); >> a = sim(net,p)

  17. An Illustrative Example A produce dealer has a warehouse that stores a variety of fruits and vegetables.When fruit is brought to the warehouse, various types of fruit maybe mixed together. The dealer wants a machine that will sort the fruit accordingto type. There is a conveyer belt on which the fruit is loaded. Thisconveyer passes through a set of sensors, which measure three properties of the fruit: shape, textureand weight. The shape sensor will output a 1 if the fruit is approximately roundand a 0 if it is more elliptical. The texture sensor will output a 1 if the surfaceof the fruit is smooth and a 0 if it is rough. The weight sensor willoutput a 1 if the fruit is more than one pound and a 0 if it is less than one pound. Pineapple Banana

  18. Perceptron Learning Rule (learnp)

More Related