1 / 13

LEARNING SEQUENCES FROM Conway’s game of life

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.

peers
Download Presentation

LEARNING SEQUENCES FROM Conway’s game of life

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. SE367 Project Final Presentation LEARNING SEQUENCES FROM Conway’s game of life By: Sujith Thomas Parimi Krishna Chaitanya In charge:- Prof Amitabha Mukerjee

  2. 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. OBJECTIVE OF THE PROJECT

  3. Simple rules of Conway’s game of life Emergence of complex patterns Backpropagated neural network Recurrent neural networks Quick Recap

  4. Training Neural Network to learn the rules of Conway’s game of life • Training a Recurrent Neural Network to detect a repeated pattern. Stages OF the project

  5. Training Neural Net to learn rules of Conway’s game of life Features of training model Input vector of size 9 Hidden layer has 9 nodes Output layer has 1 node We use bias at input and hidden layer Our activation function is sigmoid We update the weights through the backpropagation algorithm

  6. Training Neural Net to learn rules of Conway’s game of life

  7. Training a recurrent neural net for recognizing repeated patterns • 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).

  8. Training a recurrent neural net to recognize repeated patterns

  9. 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. Detecting Emergent Patterns

  10. 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. Coming to RESULTS

  11. Some of our outputs OSCILLATORS

  12. Some of our outputs Still Lives

  13. 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 References:

More Related