Balancing an Inverted Pendulum with a Multi-Layer Perceptron

Slides:



Advertisements
Similar presentations
Introduction to Neural Networks Computing
Advertisements

Ch. Eick: More on Machine Learning & Neural Networks Different Forms of Learning: –Learning agent receives feedback with respect to its actions (e.g. using.
Multilayer Perceptrons 1. Overview  Recap of neural network theory  The multi-layered perceptron  Back-propagation  Introduction to training  Uses.
Neural Networks  A neural network is a network of simulated neurons that can be used to recognize instances of patterns. NNs learn by searching through.
ETHEM ALPAYDIN © The MIT Press, Lecture Slides for.
Simple Neural Nets For Pattern Classification
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Radial Basis Functions
November 9, 2010Neural Networks Lecture 16: Counterpropagation 1 Unsupervised Learning So far, we have only looked at supervised learning, in which an.
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.
Presenting: Itai Avron Supervisor: Chen Koren Characterization Presentation Spring 2005 Implementation of Artificial Intelligence System on FPGA.
Radial Basis Function (RBF) Networks
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Objectives Identify the conditions of simple harmonic motion.
Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks.
Kumar Srijan ( ) Syed Ahsan( ). Problem Statement To create a Neural Networks based multiclass object classifier which can do rotation,
Neural Networks Ellen Walker Hiram College. Connectionist Architectures Characterized by (Rich & Knight) –Large number of very simple neuron-like processing.
Rotation Invariant Neural-Network Based Face Detection
Position Reconstruction in Miniature Detector Using a Multilayer Perceptron By Adam Levine.
Mehdi Mohammadi March Western Michigan University Department of Computer Science CS Advanced Data Structure.
So Far……  Clustering basics, necessity for clustering, Usage in various fields : engineering and industrial fields  Properties : hierarchical, flat,
Chapter 11 Preview Objectives Hooke’s Law Sample Problem
Time Parallel Simulations I Problem-Specific Approach to Create Massively Parallel Simulations.
An Artificial Neural Network Approach to Surface Waviness Prediction in Surface Finishing Process by Chi Ngo ECE/ME 539 Class Project.
Over-Trained Network Node Removal and Neurotransmitter-Inspired Artificial Neural Networks By: Kyle Wray.
Chapter 2 Single Layer Feedforward Networks
פרקים נבחרים בפיסיקת החלקיקים אבנר סופר אביב
Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.
Neural Networks 2nd Edition Simon Haykin
Modelleerimine ja Juhtimine Tehisnärvivõrgudega Identification and Control with artificial neural networks.
Artificial Intelligence Methods Neural Networks Lecture 3 Rakesh K. Bissoondeeal Rakesh K. Bissoondeeal.
Neural Networks References: “Artificial Intelligence for Games” "Artificial Intelligence: A new Synthesis"
Evolutionary Computation Evolving Neural Network Topologies.
Pattern Recognition Lecture 20: Neural Networks 3 Dr. Richard Spillman Pacific Lutheran University.
Machine Learning 12. Local Models.
Machine Learning Supervised Learning Classification and Regression
Big data classification using neural network
Multiple-Layer Networks and Backpropagation Algorithms
Chapter 5 Unsupervised learning
Section 1 Simple Harmonic Motion
Ananya Das Christman CS311 Fall 2016
Neural Networks Winter-Spring 2014
Data Mining, Neural Network and Genetic Programming
Adaptive Resonance Theory (ART)
Ch7: Hopfield Neural Model
Chapter 2 Single Layer Feedforward Networks
Modelleerimine ja Juhtimine Tehisnärvivõrgudega
Real Neurons Cell structures Cell body Dendrites Axon
A Support Vector Machine Approach to Sonar Classification
What is an ANN ? The inventor of the first neuro computer, Dr. Robert defines a neural network as,A human brain like system consisting of a large number.
Neural Networks A neural network is a network of simulated neurons that can be used to recognize instances of patterns. NNs learn by searching through.
Neural Networks: Improving Performance in X-ray Lithography Applications ECE 539 Ryan T. Hogg May 10, 2000.
Counter propagation network (CPN) (§ 5.3)
"Playing Atari with deep reinforcement learning."
Lecture 22 Clustering (3).
Chapter 3. Artificial Neural Networks - Introduction -
Training a Neural Network
Neuro-Computing Lecture 4 Radial Basis Function Network
of the Artificial Neural Networks.
Neural Networks Chapter 5
Generating Coherent Patterns of Activity from Chaotic Neural Networks
Capabilities of Threshold Neurons
CSSE463: Image Recognition Day 18
Dr. Unnikrishnan P.C. Professor, EEE
Computer Vision Lecture 19: Object Recognition III
The Network Approach: Mind as a Web
Using Clustering to Make Prediction Intervals For Neural Networks
Artificial Neural Networks / Spring 2002
Presentation transcript:

Balancing an Inverted Pendulum with a Multi-Layer Perceptron ECE 539 Final Project Spring 2000 Chad Seys

Outline The Inverted Pendulum The Problem Approach Position Representation Output Force Representation Initialization Convergence & Reinitialization Results Discussion

The Inverted Pendulum: Abstraction is a rigid rod attached at its lower end to a pivot point. Like balancing a broom on the palm of hand. Useful in modeling: Launching a rocket into space look up another

The Problem: Train a multi-layer perceptron to... keep an inverted pendulum in its upright position move an inverted pendulum from any position to the upright position (keep it balanced there).

Approach: Divide the 180 degrees into M arc segments (where M is odd). M odd to provide a central region where no force is applied. There will be M input neurons, one per segment. There will be two output neurons whose outputs will be interpreted as opposing force vectors of fixed magnitude.

Inverse Pendulum Position Representation A few of the possibilities to explore: (Chosen) A “1” in the input dimension corresponding to the arc segment which the inverse pendulum currently occupies, “0” in other dimensions. As above, but have a gradual decline to “0” in neighboring segments. Might help prevent overshoot at the top. Alternatively, put “0” to the left of inv pendulum, “0.5” at the inv pendulum, and “1” to the right of the inv pendulum. Might provide more directional information.

Output Force Representation The output neuron force vector will act perpendicularly to the center of mass of the inv pendulum. Will use a supervised learning paradigm. Training data will be a fixed correcting force to return the inverse pendulum to the vertical. Ideally would use a unsupervised learning paradigm allowing varying correcting force magnitudes, but unsure how to implement.

Initialization at top with a small movement in one or the other direction at increasing angles from the top with no movement. (not included in final version of project)

Convergence & Reinitialization The standard: Amount of match between output and the teacher’s data. Also, over how many simulation steps does the inv pendulum stay within a small number of degrees of the top. Stability. This may be the criteria for reinitialization. May not reset the network weights, only the inverse pendulum position. (did not appear in the final version of project)

H Hidden Neurons M Input M Arc Segments Fixed Output Force 1 H Hidden Neurons M Input H M Arc Segments Fixed Output Force 2 Output Neurons

Results (Force vs. Time Step): Difficult to find a balance of force and sampling interval. Using too large of a force would result in over-correction.

Results (Force vs. Time Step): Too small of a force resulted in under correction. Smaller time steps solve this problem, but increase memory usage and processing time.

Did not reach 100% convergence. Ran one promising (which appeared not to be under or over corrected) simulation for a period of several days (>69000 iterations) and achieved a convergence rate of only 61.3%. By the way the pendulum falls during the testing section of the simulation, the neural network does not yet appear to have “learned” to balance the inverse pendulum.

Results Did not succeed in balancing a inverse pendulum during the duration of the simulation runs.