learning sequences from conway’s game of life

13
SE367 Project Final Presentation By: Sujith Thomas Parimi Krishna Chaitanya In charge:- Prof Amitabha Mukerjee

Upload: peers

Post on 06-Jan-2016

26 views

Category:

Documents


3 download

DESCRIPTION

SE367 Project Final Presentation. LEARNING SEQUENCES FROM Conway’s game of life. By: Sujith Thomas Parimi Krishna Chaitanya In charge:- Prof Amitabha Mukerjee. To make a neural net learn the rules of Conway’s game of life and predict the next generation of cells. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: LEARNING SEQUENCES FROM Conway’s game of life

SE367 Project Final Presentation

By:Sujith Thomas

Parimi Krishna Chaitanya

In charge:- Prof Amitabha Mukerjee

Page 2: LEARNING SEQUENCES FROM Conway’s game of life

To make a neural net learn the rules of Conway’s game of life and predict the next generation of cells.

To identify oscillators and other emergent patterns using recurrent neural networks.

Page 3: LEARNING SEQUENCES FROM Conway’s game of life

Simple rules of Conway’s game of life

Emergence of complex patterns

Backpropagated neural network

Recurrent neural networks

Page 4: LEARNING SEQUENCES FROM Conway’s game of life

Training Neural Network to learn the rules of Conway’s game of life

Training a Recurrent Neural Network to detect a repeated pattern.

Page 5: LEARNING SEQUENCES FROM Conway’s game of life

1. Input vector of size 9

2. Hidden layer has 9 nodes3. Output layer has 1 node

4. We use bias at input and hidden layer

5. Our activation function is sigmoid

6. We update the weights through the backpropagation algorithm

Features of training model

Page 6: LEARNING SEQUENCES FROM Conway’s game of life
Page 7: LEARNING SEQUENCES FROM Conway’s game of life

Input vector of size 18 Hidden layer has 18 nodes Output layer has 2 nodes Bias is present at each layer Activation function is Sigmoid We are again updating weights

through backpropagation. In input vector the last 9

dimensions correspond to previous delayed state as shown.

We are using an array to store the previous 12 output states (size may vary later).

Page 8: LEARNING SEQUENCES FROM Conway’s game of life
Page 9: LEARNING SEQUENCES FROM Conway’s game of life

The game has cells of 12 rows and 12 columns .

We use a seed of size 3X3 and4X4 to initialize the game.

We use a activation feedback from the output layer with a delay of 12 ticks.

This helps us to detect oscillators with period 1,2,3,4,6.

Page 10: LEARNING SEQUENCES FROM Conway’s game of life

Till now we have detected still lives and oscillators. Till final demonstration we will show Gliders after

they are recognized. The problem with gliders comes with their property of “Translation”

For solving this we can either use a 4 layer Neural Network or we have a heuristic of re-seeding.

Page 11: LEARNING SEQUENCES FROM Conway’s game of life

OSCILLATORS

Page 12: LEARNING SEQUENCES FROM Conway’s game of life

Still Lives

Page 13: LEARNING SEQUENCES FROM Conway’s game of life

A guide to Recurrent Neural Networks and Backpropagation, Mikael Boden, Halmstad University 2001.

Pattern Classification – Duda, Hart and Stork

Wikipedia – Conway’s Game of Life Implementation of Neural Networks in C -

John Bullinaria, University of Birmingham. http://www.cs.bham.ac.uk/~jxb/NN/nn.html