Implementing Local Relative Sensitivity Pruning Paul Victorey.

Slides:



Advertisements
Similar presentations
Multi-Layer Perceptron (MLP)
Advertisements

NEURAL NETWORKS Backpropagation Algorithm
Multilayer Perceptrons 1. Overview  Recap of neural network theory  The multi-layered perceptron  Back-propagation  Introduction to training  Uses.
Brain Damage: Algorithms for Network Pruning Andrew Yip HMC Fall 2003.
CS 4700: Foundations of Artificial Intelligence
Kostas Kontogiannis E&CE
Music Analysis Josiah Boning TJHSST Senior Research Project Computer Systems Lab,
Machine Learning Neural Networks
1 Part I Artificial Neural Networks Sofia Nikitaki.
Handwritten Character Recognition Using Artificial Neural Networks Shimie Atkins & Daniel Marco Supervisor: Johanan Erez Technion - Israel Institute of.
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Prénom Nom Document Analysis: Linear Discrimination Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Neural Networks Marco Loog.
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
November 2, 2010Neural Networks Lecture 14: Radial Basis Functions 1 Cascade Correlation Weights to each new hidden node are trained to maximize the covariance.
Chapter 6: Multilayer Neural Networks
1 Automated Feature Abstraction of the fMRI Signal using Neural Network Clustering Techniques Stefan Niculescu and Tom Mitchell Siemens Medical Solutions,
MAE 552 Heuristic Optimization Instructor: John Eddy Lecture #31 4/17/02 Neural Networks.
Information Fusion Yu Cai. Research Article “Comparative Analysis of Some Neural Network Architectures for Data Fusion”, Authors: Juan Cires, PA Romo,
Hub Queue Size Analyzer Implementing Neural Networks in practice.
Hazırlayan NEURAL NETWORKS Radial Basis Function Networks II PROF. DR. YUSUF OYSAL.
Radial Basis Function Networks
A Genetic Algorithms Approach to Feature Subset Selection Problem by Hasan Doğu TAŞKIRAN CS 550 – Machine Learning Workshop Department of Computer Engineering.
Soft Computing Lecture 18 Foundations of genetic algorithms (GA). Using of GA.
11 CSE 4705 Artificial Intelligence Jinbo Bi Department of Computer Science & Engineering
Introduction to Artificial Neural Network Models Angshuman Saha Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg.
NEURAL NETWORKS FOR DATA MINING
Radial Basis Function Networks:
An informal description of artificial neural networks John MacCormick.
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Last lecture summary. biologically motivated synapses Neuron accumulates (Σ) positive/negative stimuli from other neurons. Then Σ is processed further.
Soft Computing Lecture 8 Using of perceptron for image recognition and forecasting.
Non-Bayes classifiers. Linear discriminants, neural networks.
ELeaRNT: Evolutionary Learning of Rich Neural Network Topologies Authors: Slobodan Miletic 3078/2010 Nikola Jovanovic 3077/2010
A Simulated-annealing-based Approach for Simultaneous Parameter Optimization and Feature Selection of Back-Propagation Networks (BPN) Shih-Wei Lin, Tsung-Yuan.
Intro. ANN & Fuzzy Systems Lecture 14. MLP (VI): Model Selection.
Feature selection with Neural Networks Dmitrij Lagutin, T Variable Selection for Regression
CSC321: Lecture 7:Ways to prevent overfitting
Introduction to Neural Networks Introduction to Neural Networks Applied to OCR and Speech Recognition An actual neuron A crude model of a neuron Computational.
Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg
Evolving RBF Networks via GP for Estimating Fitness Values using Surrogate Models Ahmed Kattan Edgar Galvan.
CHEE825 Fall 2005J. McLellan1 Nonlinear Empirical Models.
Bab 5 Classification: Alternative Techniques Part 4 Artificial Neural Networks Based Classifer.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
Neural Networks The Elements of Statistical Learning, Chapter 12 Presented by Nick Rizzolo.
Tree and Forest Classification and Regression Tree Bagging of trees Boosting trees Random Forest.
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
Machine Learning Supervised Learning Classification and Regression
Artificial Neural Networks
MATLAB Implementation of the Optimal Brain Surgeon (OBS) Algorithm
ECE 539 Final Project Mark Slosarek
Java Implementation of Optimal Brain Surgeon
Going Backwards In The Procedure and Recapitulation of System Identification By Ali Pekcan 65570B.
Generalization ..
Machine Learning Today: Reading: Maria Florina Balcan
Optimal Brain Surgeon Algorithm
Forward & Backward selection in hybrid network
Approximate Fully Connected Neural Network Generation
Chap. 7 Regularization for Deep Learning (7.8~7.12 )
Artificial Neural Networks
Introduction to Neural Networks And Their Applications - Basics
Neural Networks Geoff Hulten.
Capabilities of Threshold Neurons
Lecture Notes for Chapter 4 Artificial Neural Networks
Evolutionary Algorithms for Hyperparameter Optimization
COSC 4335: Part2: Other Classification Techniques
Computer Vision Lecture 19: Object Recognition III
III. Introduction to Neural Networks And Their Applications - Basics
Neural Network Training
CSC 578 Neural Networks and Deep Learning
Presentation transcript:

Implementing Local Relative Sensitivity Pruning Paul Victorey

Why Prune? It is believed that neural networks with too many connections tend to have more capacity for learning training set error. Pruning has been shown to reduce testing error. Pruning has been shown to yield a more favorable generalization factor (closer to 1).

Pruning Strategies Optimal Brain Surgeon (OBS) and Optimal Brain Damage (OBD) are widely used, but are computationally expensive. Karnin proposes using “Sensitivity value” (SV) as pruning criteria. The SV is defined as: Local Relative Sensitivity Pruning (LRSP) is similar to the SV approach. It considers local as well as global effects of pruning. The LRSI is the SV of the given weight divided by the sum of the SVs of the weight’s local group; a local group is the collection of weights which are associated with the inputs to a single neuron.

LRSP Algorithm Partition data into training, validation, and testing sets. Use training set to train a fully connected MLP. Compute the LRSI for each weight. Prune at most one input to any given node; prune only if a weight has a LRSI less than a threshold (0.01 seems to work). Retrain the pruned network. Evaluate the performance of this network compared to the network pre-pruning. If the network is better, keep the new network, and perform pruning again. When the network shows no improvement, stop. Several possible cost functions to determine network fitness exist. Most popular: Validation error, Generalization Factor (when determining GF, validation error is used to approximate testing error)

Results Ponnapalli et al have shown that this method is preferable to the SV-pruning proposed by Karnin Networks pruned by LRSP in many cases approach a unity GF, and have a better testing error than pre-pruning. The positive results, coupled with a low computational overhead, make LRSP a good choice of pruning algorithm.