Download presentation
Presentation is loading. Please wait.
1
Presenting: Itai Avron Supervisor: Chen Koren Mid Semester Presentation Spring 2005 Implementation of Artificial Intelligence System on FPGA
2
Project Goals Creating a VHDL design of a Neural Network Comparison Vs. software implementation (Matlab)
3
Background Neural Network is a Learning Machine It is build from Neurons (Perceptrons), which holds the knowledge of the system within their inter-connection strength Every Neuron Implement the Active Function:
4
System Interface Input: - Image (16x16 pixels) - Weights Output: - A number between 0-9 (4 bit vector)
5
System Architecture MAX Net #0 Net #1 Net #2 Net #9 … Image Register clk resetN net_sel img_en img w ready digit
6
Net Architecture control SRAM (Xilinx) Neuron w flag Result register result img clk resetN start
7
Neuron Architecture Multipliers for calculating (Xilinx) Adders for calculating (Xilinx) SRAM implementing Activation Function Registers saving weights
8
Controller – Flow Diagram Idle Upload Image and Weights Calculate Hidden Layer Calculate Exit Layer New Image Until all Neurons are calculated Upload weight to Neuron Neuron Calculation Save Neuron Result
9
Still to do Matlab simulation (calculate weights) System improvements VHDL code debugging Final Presentation: ~ October
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.