A Dynamic System Analysis of Simultaneous Recurrent Neural Network

Slides:



Advertisements
Similar presentations
Multi-Layer Perceptron (MLP)
Advertisements

Bioinspired Computing Lecture 16
Pattern Association.
Coordination of Multi-Agent Systems Mark W. Spong Donald Biggar Willett Professor Department of Electrical and Computer Engineering and The Coordinated.
A Brief Overview of Neural Networks By Rohit Dua, Samuel A. Mulder, Steve E. Watkins, and Donald C. Wunsch.
NEURAL NETWORKS Backpropagation Algorithm
1 Machine Learning: Lecture 4 Artificial Neural Networks (Based on Chapter 4 of Mitchell T.., Machine Learning, 1997)
Introduction to Neural Networks Computing
CSC321: 2011 Introduction to Neural Networks and Machine Learning Lecture 7: Learning in recurrent networks Geoffrey Hinton.
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.
IFAC AIRTC, Budapest, October 2000 On the Dynamic Instability of a Class of Switching System Robert Noel Shorten Department of Computer Science National.
Tuomas Sandholm Carnegie Mellon University Computer Science Department
CS 678 –Relaxation and Hopfield Networks1 Relaxation and Hopfield Networks Totally connected recurrent relaxation networks Bidirectional weights (symmetric)
Machine Learning Neural Networks
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Carla P. Gomes CS4700 CS 4700: Foundations of Artificial Intelligence Prof. Carla P. Gomes Module: Neural Networks: Concepts (Reading:
Hypercubes and Neural Networks bill wolfe 10/23/2005.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
CSC 4510 – Machine Learning Dr. Mary-Angela Papalaskari Department of Computing Sciences Villanova University Course website:
CS623: Introduction to Computing with Neural Nets (lecture-10) Pushpak Bhattacharyya Computer Science and Engineering Department IIT Bombay.
Artificial Neural Networks
Computer Science and Engineering
© 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.
What is a neural network? Collection of interconnected neurons that compute and generate impulses. Components of a neural network include neurons, synapses,
NEURAL NETWORKS FOR DATA MINING
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Simultaneous Recurrent Neural Networks for Static Optimization Problems By: Amol Patwardhan Adviser: Dr. Gursel Serpen August, 1999 The University of.
Reinforcement Learning Control with Robust Stability Chuck Anderson, Matt Kretchmar, Department of Computer Science, Peter Young, Department of Electrical.
Akram Bitar and Larry Manevitz Department of Computer Science
Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.
Back-Propagation Algorithm AN INTRODUCTION TO LEARNING INTERNAL REPRESENTATIONS BY ERROR PROPAGATION Presented by: Kunal Parmar UHID:
1 Lecture 6 Neural Network Training. 2 Neural Network Training Network training is basic to establishing the functional relationship between the inputs.
Introduction to Neural Networks Introduction to Neural Networks Applied to OCR and Speech Recognition An actual neuron A crude model of a neuron Computational.
Lecture 5 Neural Control
Chapter 18 Connectionist Models
CHEE825 Fall 2005J. McLellan1 Nonlinear Empirical Models.
Artificial Neural Networks (ANN). Artificial Neural Networks First proposed in 1940s as an attempt to simulate the human brain’s cognitive learning processes.
Chapter 6 Neural Network.
Dynamic Neural Network Control (DNNC): A Non-Conventional Neural Network Model Masoud Nikravesh EECS Department, CS Division BISC Program University of.
Machine Learning Artificial Neural Networks MPλ ∀ Stergiou Theodoros 1.
A PID Neural Network Controller
Pattern Recognition Lecture 20: Neural Networks 3 Dr. Richard Spillman Pacific Lutheran University.
J. Kubalík, Gerstner Laboratory for Intelligent Decision Making and Control Artificial Neural Networks II - Outline Cascade Nets and Cascade-Correlation.
6.5.4 Back-Propagation Computation in Fully-Connected MLP.
Today’s Lecture Neural networks Training
Bayesian Neural Networks
CS 388: Natural Language Processing: Neural Networks
Artificial Neural Networks
Randomness in Neural Networks
Extreme Learning Machine
Real Neurons Cell structures Cell body Dendrites Axon
RECURRENT NEURAL NETWORKS FOR VOICE ACTIVITY DETECTION
CSE P573 Applications of Artificial Intelligence Neural Networks
Prof. Carolina Ruiz Department of Computer Science
RNNs: Going Beyond the SRN in Language Prediction
CSE 573 Introduction to Artificial Intelligence Neural Networks
Artificial Neural Networks
OCNC Statistical Approach to Neural Learning and Population Coding ---- Introduction to Mathematical.
The use of Neural Networks to schedule flow-shop with dynamic job arrival ‘A Multi-Neural Network Learning for lot Sizing and Sequencing on a Flow-Shop’
Neural Networks Geoff Hulten.
Masoud Nikravesh EECS Department, CS Division BISC Program
CSC321: Neural Networks Lecture 11: Learning in recurrent networks
August 8, 2006 Danny Budik, Itamar Elhanany Machine Intelligence Lab
CS621: Artificial Intelligence Lecture 22-23: Sigmoid neuron, Backpropagation (Lecture 20 and 21 taken by Anup on Graphical Models) Pushpak Bhattacharyya.
CS623: Introduction to Computing with Neural Nets (lecture-11)
2019/9/14 The Deep Learning Vision for Heterogeneous Network Traffic Control Proposal, Challenges, and Future Perspective Author: Nei Kato, Zubair Md.
Akram Bitar and Larry Manevitz Department of Computer Science
Prof. Carolina Ruiz Department of Computer Science
Presentation transcript:

A Dynamic System Analysis of Simultaneous Recurrent Neural Network Dr. Gursel Serpen and Mr. Yifeng Xu Electrical Engineering and Computer Science Department University of Toledo Toledo, Ohio, USA

Introduction Motivation for research Simultaneous Recurrent Neural Network (SRN) Local Stability of SRN Global stability of SRN FOR MORE INFO... Werbos, Paul  many recent articles – some unpublished! Serpen et al., The Simultaneous Recurrent Neural Network for Addressing the Scaling Problem in Static Optimization, Neural Systems, Vol. 11, No. 5, 2001, pp. 477-487.

Motivation Simultaneous Recurrent Neural (SRN) network has been shown to have the potential to address large-scale static optimization problems: located relatively high quality solutions. SRN is trainable: implies that it can learn from prior search attempts (A Hopfield net cannot do this!) Computational complexity for SRN simulations is much less again compared to the Hopfield and its derivatives.

Research Goals Understand the stability and convergence properties of the SRN dynamics. Establish stable dynamics following initialization. Establish stability while training the SRN with a fixed-point algorithm (recurrent backprop). Apply the SRN to (large-scale) static optimization problems.

Research Goals - detailed Initialization of weights to guarantee existence of at least one or more fixed points in the state space of the SRN dynamics. Stability as weight matrices are being modified while learning with a fixed-point algorithm, i.e., recurrent backpropagation. Assessing the computational power of the SRN as a static optimizer for large-scale problem instances.

Simultaneous Recurrent Neural Network Topology Feedforward Network Input Output Typical propagation delay exists on the feedback path as dictated by physical constraints! Delayed Feedback

SRN Detailed Structure – 3 Layers x y W U z V Propagation Delay outputs z = f (Uy) and y = f (Wx+Vz)

Analysis of SRN Dynamics Local stability analysis SRN dynamics linearized at hypercube corners (that are also equilibrium points) (Local) stability conditions for hypercube corner equilibrium points A theorem...its proof (elsewhere)

Equilibrium Points in State Space of SRN Dynamics Output layer Hidden layer SRN dynamics in matrix form in terms of z:

Equilibrium Points of SRN Dynamics Hypercube Corners zk = 1 or zk = 0 for k = 1, 2, …, K Points interior, on the surface, and on the edges of the hypercube

Stability of SRN Dynamics - Linearized Eigenvalues of SRN dynamics linearized at hypercube corners (equilibrium points): for k = 1, 2, … , K.

Stability of SRN Dynamics - linearized Set of inequalities derived from eigenvalues through stability condition for equilibrium points. = 0 for for = 1

A Stability Theorem for SRN Dynamics For any given hypercube corner in the state space of SRN dynamics, which is configured for static combinatorial optimization, i.e. with high-gain neurons, one hidden layer, one output layer, no external input, and operating in associative memory mode, it is possible to define the weight matrices U and V to establish that hypercube corner as a stable equilibrium point in a local sense.

Simulation Study Fixed points (hypercube corners) 48 Case 1 - 2X4 SRN Methodology: Create 75 instances of U & V then, observe set of stable equilibrium points thru multiple random initializations. Fixed points (hypercube corners) 48 Limit cycles - cycle length of 2 12 Stable non-hypercube points 19 * all 16 hypercube corners appeared as stable equilibrium points for 75 instances of weight matrices. Case 2 - 2X100 SRN Case 3 - 5X10000 SRN Case 4 - 5X25000 SRN

Global Stability of SRN? The SRN paradigm is closely related to a number of globally asymptotically stable recurrent neural network algorithms! BAM is a special case of SRN. ART 1 & 2 cores are similar topologies. Significant simulation-based empirical studies conducted by authors suggest global stability. However, no Liapunov function yet!

Conclusions A theorem demonstrates that there exist real forward and backward weight matrices for SRN dynamics, which will induce stability of any given hypercube corner as an equilibrium point. This theoretical finding was also validated by extensive simulation-based empirical studies, some of which was reported in a recent journal article: Serpen et al., The Simultaneous Recurrent Neural Network for Addressing the Scaling Problem in Static Optimization, Neural Systems, Vol. 11, No. 5, 2001, pp. 477-487.

Thank You ! Questions ? This research has been funded in part by the US National Science Foundation grant ECS-9800247.