1 / 12

Biological Inspiration for Artificial Neural Networks

Biological Inspiration for Artificial Neural Networks. Nick Mascola. Artificial Neuron. Basic Structure. Output=f( Σ (Weights*Inputs)). Several Layered Network. A Typical Network Organizes these Neurons into layers that feed into each other sequentially. Typical Transfer Functions.

akina
Download Presentation

Biological Inspiration for Artificial Neural Networks

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. Biological Inspiration for Artificial Neural Networks Nick Mascola

  2. Artificial Neuron Basic Structure Output=f(Σ(Weights*Inputs))

  3. Several Layered Network A Typical Network Organizes these Neurons into layers that feed into each other sequentially

  4. Typical Transfer Functions

  5. Recall that Over Time:

  6. Finite Amount of Resources

  7. Implementation • void distributeweightpoints(Connections con){ • vector<Weight> list = con.weights; • int totalpoints=con.points; • double total=weightsummation(list); • double temp; • for(unsigned int i=0; i<con.weights.size(); i++){ • temp=list[i].value/total; • if(temp<1/totalpoints){ • con.weights[i]=0;} • else{ • con.weights[i]=temp;} • } • }

  8. Long Term Potentiation Features Similar to ANN Functionality: Cooperativity Specificity

  9. Distinct Feature Associativity

  10. Possible Solution

  11. …Or More Generally

  12. References • http://hagan.ecen.ceat.okstate.edu/nnd.html • Matlab Neural Network Toolbox • Pattern Classification (2nd ed) by Richard O. Duda, Peter E. Hart and David G. Stork • Pattern Recognition and Machine Learning. Christopher M. Bishop • The long-term potential of LTP Robert C.Malenka

More Related