Neural Net Update Dave Bailey. What’s New You can now save and load datasets from a file e.g. saving the dataset: You can now save and load datasets from.

Slides:



Advertisements
Similar presentations
Beyond Linear Separability
Advertisements

Slides from: Doug Gray, David Poole
NEURAL NETWORKS Backpropagation Algorithm
Learning in Neural and Belief Networks - Feed Forward Neural Network 2001 년 3 월 28 일 안순길.
Neural networks Introduction Fitting neural networks
1 Machine Learning: Lecture 4 Artificial Neural Networks (Based on Chapter 4 of Mitchell T.., Machine Learning, 1997)
CSC321: 2011 Introduction to Neural Networks and Machine Learning Lecture 7: Learning in recurrent networks Geoffrey Hinton.
Deep Learning and Neural Nets Spring 2015
CSCI 347 / CS 4206: Data Mining Module 07: Implementations Topic 03: Linear Models.
Tuomas Sandholm Carnegie Mellon University Computer Science Department
Unsupervised Learning with Artificial Neural Networks The ANN is given a set of patterns, P, from space, S, but little/no information about their classification,
The loss function, the normal equation,
Classification and Prediction: Regression Via Gradient Descent Optimization Bamshad Mobasher DePaul University.
Hidden Markov Models Theory By Johan Walters (SR 2003)
Sparse vs. Ensemble Approaches to Supervised Learning
September 23, 2010Neural Networks Lecture 6: Perceptron Learning 1 Refresher: Perceptron Training Algorithm Algorithm Perceptron; Start with a randomly.
Sparse vs. Ensemble Approaches to Supervised Learning
CS 4700: Foundations of Artificial Intelligence
Neural Network Tools. Neural Net Concepts The package provides a “standard” multi-layer perceptron –Composed of layers of neurons –All neurons in a layer.
Implementation of Nonlinear Conjugate Gradient Method for MLP Matt Peterson ECE 539 December 10, 2001.
UNCONSTRAINED MULTIVARIABLE
Collaborative Filtering Matrix Factorization Approach
Principle Component Analysis (PCA) Networks (§ 5.8) PCA: a statistical procedure –Reduce dimensionality of input vectors Too many features, some of them.
Evolving a Sigma-Pi Network as a Network Simulator by Justin Basilico.
Artificial Neural Networks
1 Artificial Neural Networks Sanun Srisuk EECP0720 Expert Systems – Artificial Neural Networks.
© Copyright 2004 ECE, UM-Rolla. All rights reserved A Brief Overview of Neural Networks By Rohit Dua, Samuel A. Mulder, Steve E. Watkins, and Donald C.
EMIS 8381 – Spring Netflix and Your Next Movie Night Nonlinear Programming Ron Andrews EMIS 8381.
Neural Networks1 Introduction to NETLAB NETLAB is a Matlab toolbox for experimenting with neural networks Available from:
Artificial Neural Networks. The Brain How do brains work? How do human brains differ from that of other animals? Can we base models of artificial intelligence.
M Machine Learning F# and Accord.net. Alena Dzenisenka Software architect at Luxoft Poland Member of F# Software Foundation Board of Trustees Researcher.
CS 782 – Machine Learning Lecture 4 Linear Models for Classification  Probabilistic generative models  Probabilistic discriminative models.
Linear Discrimination Reading: Chapter 2 of textbook.
Non-Bayes classifiers. Linear discriminants, neural networks.
Akram Bitar and Larry Manevitz Department of Computer Science
11 1 Backpropagation Multilayer Perceptron R – S 1 – S 2 – S 3 Network.
An Artificial Neural Network Approach to Surface Waviness Prediction in Surface Finishing Process by Chi Ngo ECE/ME 539 Class Project.
M Machine Learning F# and Accord.net.
Robert J. Marks II CIA Lab Baylor University School of Engineering CiaLab.org Artificial Neural Networks: Supervised Models.
Artificial Neural Networks (Cont.) Chapter 4 Perceptron Gradient Descent Multilayer Networks Backpropagation Algorithm 1.
Logistic Regression William Cohen.
Hand-written character recognition
1 Perceptron as one Type of Linear Discriminants IntroductionIntroduction Design of Primitive UnitsDesign of Primitive Units PerceptronsPerceptrons.
Artificial Intelligence Methods Neural Networks Lecture 3 Rakesh K. Bissoondeeal Rakesh K. Bissoondeeal.
1 Learning Bias & Clustering Louis Oliphant CS based on slides by Burr H. Settles.
1 Technological Educational Institute Of Crete Department Of Applied Informatics and Multimedia Intelligent Systems Laboratory.
Bab 5 Classification: Alternative Techniques Part 4 Artificial Neural Networks Based Classifer.
BACKPROPAGATION (CONTINUED) Hidden unit transfer function usually sigmoid (s-shaped), a smooth curve. Limits the output (activation) unit between 0..1.
Bump Hunting The objective PRIM algorithm Beam search References: Feelders, A.J. (2002). Rule induction by bump hunting. In J. Meij (Ed.), Dealing with.
WEEK 2 SOFT COMPUTING & MACHINE LEARNING YOSI KRISTIAN Gradient Descent for Linear Regression.
Local Search Goal is to find the local maximum (or minimum) Example: – # seconds to spin wheels at 1.0 to move 2.0 meters.
Pattern Recognition Lecture 20: Neural Networks 3 Dr. Richard Spillman Pacific Lutheran University.
Today’s Lecture Neural networks Training
Neural networks and support vector machines
Soft Computing Applied to Finite Element Tasks
Announcements HW4 due today (11:59pm) HW5 out today (due 11/17 11:59pm)
Classification with Perceptrons Reading:
Generalization ..
Linear Discriminators
Blind Signal Separation using Principal Components Analysis
Collaborative Filtering Matrix Factorization Approach
Outline Single neuron case: Nonlinear error correcting learning
cs540 - Fall 2016 (Shavlik©), Lecture 18, Week 10
The loss function, the normal equation,
Mathematical Foundations of BME Reza Shadmehr
Neural networks (1) Traditional multi-layer perceptrons
Nonlinear Conjugate Gradient Method for Supervised Training of MLP
Introduction to Neural Networks
Akram Bitar and Larry Manevitz Department of Computer Science
Presentation transcript:

Neural Net Update Dave Bailey

What’s New You can now save and load datasets from a file e.g. saving the dataset: You can now save and load datasets from a file e.g. saving the dataset: NeuralNetDataSet myDataSet; … // Fill the DataSet std::ofstream ofs; ofs.open(“myfile.dat”,std::ios_base::out|std::ios_base::trunc); if (ofs.is_open()) { ofs << myDataSet; // Writes the dataset to the stream ofs.close(); }

What’s New (2) Loading a previously saved dataset: std::string filename(“myfile.dat”); NeuralNetDataSet myDataSet(filename); DataSets are saved to a plain text file So be warned, the files can be quite large if you have a lot of data in them You can use as many different datasets as you like to train the network DataSets are saved to a plain text file So be warned, the files can be quite large if you have a lot of data in them You can use as many different datasets as you like to train the network

Feature Fixes There was a problem with part of the conjugate gradients training algorithm Showed up as big jumps in the error function whilst training Due to an oversight (and a small bug) in the linear search that optimises the training step length There was a problem with part of the conjugate gradients training algorithm Showed up as big jumps in the error function whilst training Due to an oversight (and a small bug) in the linear search that optimises the training step length

Search Technique Remember that the network “learns” by The conjugate gradient method attempts to optimise λ and μ for each epoch Remember that the network “learns” by The conjugate gradient method attempts to optimise λ and μ for each epoch

Linear Search Optimisation is performed using a linear search along a direction in “weight space”, looking for the minimum of the error function Slope -σψ’(0)Slope σψ’(0) ψ(0)+step*μψ’(0) Slope ψ’(0) μ,σ are search parameters Try to end up here

Problem and Solution Basic assumption was that the minimum would be found for positive step lengths Not true in real life as the starting point could be anywhere in weight space Line search is now bi-directional i.e. can search backwards up the direction vector Convergence much more stable and the problem of jumping error function is gone Basic assumption was that the minimum would be found for positive step lengths Not true in real life as the starting point could be anywhere in weight space Line search is now bi-directional i.e. can search backwards up the direction vector Convergence much more stable and the problem of jumping error function is gone