DOC PREVIEW
BYU BIO 465 - Biological inspiration

This preview shows page 1-2-3-4-5 out of 16 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 16 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 16 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 16 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 16 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 16 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 16 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Biological inspirationSlide 2Slide 3Artificial neuronsArtificial neural networksLearning in biological systemsNeural network mathematicsNeural network approximationLearning with MLP neural networksLearning with backpropagationPowerPoint PresentationSlide 12Artificial Neural NetworkDangerProfile network from HeiDelbergPHDBiological inspirationAnimals are able to react adaptively to changes in their external and internal environment, and they use their nervous system to perform these behaviours.An appropriate model/simulation of the nervous system should be able to produce similar responses and behaviours in artificial systems.The nervous system is build by relatively simple units, the neurons, so copying their behavior and functionality should be the solution.Biological inspirationDendritesSoma (cell body)AxonBiological inspirationsynapsesaxondendritesThe information transmission happens at the synapses.Artificial neuronsNeurons work by processing information. They receive and provide information in form of spikes.The McCullogh-Pitts modelInputsOutputw2w1w3wnwn-1...x1x2x3…xn-1xny)(;1zHyxwzniii==∑=Artificial neural networksInputsOutputAn artificial neural network is composed of many artificial neurons that are linked together according to a specific network architecture. The objective of the neural network is to transform the inputs into meaningful outputs.Learning in biological systemsLearning = learning by adaptationThe young animal learns that the green fruits are sour, while the yellowish/reddish ones are sweet. The learning happens by adapting the fruit picking behavior.At the neural level the learning happens by changing of the synaptic strengths, eliminating some synapses, and building new ones.Neural network mathematicsInputsOutput),(),(),(),(14414133131221211111wxfywxfywxfywxfy====),(),(),(231232212221121wyfywyfywyfy===⎟⎟⎟⎟⎟⎠⎞⎜⎜⎜⎜⎜⎝⎛=141312111yyyyy),(312wyfyOut=⎟⎟⎟⎟⎠⎞⎜⎜⎜⎜⎝⎛=2323232yyyyNeural network approximationTask specification:Data: set of value pairs: (xt, yt), yt=g(xt) + zt; zt is random measurement noise.Objective: find a neural network that represents the input / output transformation (a function) F(x,W) such thatF(x,W) approximates g(x) for every xLearning with MLP neural networksMLP neural network:with p layersData:),(),...,,(),,(2211NNyxyxyxError:22));(())(()(ttto utyWxFytytE −=−=It is very complicated to calculate the weight changes.xyout 1 2 … p-1 pLearning with backpropagationSolution of the complicated learning:• calculate first the changes for the synaptic weights of the output neuron;• calculate the changes backward starting from layer p-1, and propagate backward the local error terms.The method is still relatively complicated but it is much simpler than the original optimisation problem..2 .8.3 .4.1 .6Train = 1.151 0.2*1+.8*0=.2.3*1+.4*0=.3.1*.3+.6*.2=.15Error = 1-.15=.85.6 .8.4 .4.2 .8Train = 1.720 1.6*0+.8*1=.8.4*0+.4*1=.4.2*.4+.8*.8=.72Error = 1-.72=.28Train 1Error 0.85Value 0.15Weights 0.1 0.6Percent 20% 80%Error 0.17 0.68Values 0.3 0.2Weights 0.3 0.4 0.2 0.8Percent 100% 0% 100% 0%Error 0.17 0 0.68 0Inputs 1 0Train 1.00Error 0.28Value 0.72Weights 0.20 0.8Percent 11% 89%Error 0.03 0.25Values 0.4 0.8Weights 0.4 0.4 0.6 0.8Percent 0% 100% 0% 100%Error 0.00 0.03 0.00 0.25Inputs 0 1.6 .9.4 .45.25 .9Train = 01.561 1.6*1+.9*1=1.5.4*1+.45*1=.85.25*.85+.9*.1.5=1.56Error = 0-1.56=-1.56Train 0Error -1.56Value 1.56Weights 0.25 0.9Percent 14% 86%Error -0.21 -1.35Values 0.85 1.5Weights 0.4 0.45 0.6 0.9Percent 47% 53% 40% 60%Error -0.10 -0.11 -0.54 -0.81Inputs 1 1Artificial Neural NetworkPredictsStructure at this pointDangerYou may train the network on your training set, but it may not generalize to other dataPerhaps we should train several ANNs and then let them vote on the structureProfile network from HeiDelbergfamily (alignment is used as input) instead of just the new sequenceOn the first level, a window of length 13 around the residue is used The window slides down the sequence, making a prediction for each residueThe input includes the frequency of amino acids occurring in each position in the multiple alignment (In the example, there are 5 sequences in the multiple alignment)The second level takes these predictions from neural networks that are centered on neighboring proteins The third level does a jury selectionPHDPredicts 4Predicts 6Predicts 6Predicts 5Predicts


View Full Document

BYU BIO 465 - Biological inspiration

Documents in this Course
summary

summary

13 pages

Cancer

Cancer

8 pages

Ch1

Ch1

5 pages

GNUMap

GNUMap

20 pages

cancer

cancer

8 pages

SNPs

SNPs

22 pages

Load more
Download Biological inspiration
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Biological inspiration and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Biological inspiration 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?