60 likes | 84 Views
Learn about the Optimal Brain Surgeon Algorithm, how it reduces the complexity of neural networks, and its benefits such as quicker calculations and reduced storage space. Follow the steps to perform the algorithm, understand the tests performed, and explore the results obtained using the wine data. Conclude with insights on the algorithm's effectiveness and potential improvements for real-world applications.
E N D
Optimal Brain Surgeon ECE 539 Final Project Mark Slosarek
Background • Optimal Brain Surgeon Algorithm (OBS) is a pruning algorithm • Reduces weights to reduce overall complexity of network
Benefits • A pruned network has several benefits • Quicker Calculations • Less Storage Space required • A pruned network should not have significantly more error than an non-pruned network
Steps to Perform OBS • Train the given MLP to minimize mean-square error • Calculate the cost of the equation • Compute the inverse Hessian • Find the smallest Saliency • If Saliency is much smaller than mean-square, delete that weight and repeat for next weight, other go to next step • Update all weights
Tests Performed and Results • To test the effectiveness of the OSB, I used the wine data from the homework • The pruned network contained approximately 60% fewer weights • Results from both networks, however results of pruning were very inconclusive • The results were not very consistant
Conclusion • A pruned network can save much space and time • My algorithm is not perfect, and could be recoded to be more efficient • Results not noticeable in simple networks, but in real world problems, could be results could be great