logging in or signing up FINAL PRESENTATION chandru210486 Download Post to : URL : Related Presentations : Share Add to Flag Embed Email Send to Blogs and Networks Add to Channel Uploaded from authorPOINT Insert YouTube videos in PowerPont slides with aS Desktop Copy embed code: (To copy code, click on the text box) Embed: URL: Thumbnail: WordPress Embed Customize Embed The presentation is successfully added In Your Favorites. Views: 802 Category: Entertainment License: All Rights Reserved Like it (0) Dislike it (0) Added: August 17, 2007 This Presentation is Public Favorites: 0 Presentation Description No description available. Comments Posting comment... By: yogeshmanohar (22 month(s) ago) good Saving..... Post Reply Close Saving..... Edit Comment Close Premium member Presentation Transcript NEURAL NETWORK BASED ROBOT NAVIGATOR: NEURAL NETWORK BASED ROBOT NAVIGATOR BY, S.CHANDRASEKARAN H.JAIDEV S.KARTHIK OBJECTIVE: OBJECTIVE To navigate from one place to another by avoiding the obstacles automatically without any human intervention ANN : ANN A system Loosely modeled on human brain. Supervised learning. Needs both predictor and target variables The goal is to achieve the desired target. Unsupervised Learning. All variables are same. The goal is to look for patterns, clusters. MLFN DIAGRAM: MLFN DIAGRAM LAYERS OF MLFN: LAYERS OF MLFN Input layer Predictor variables. Hidden layer Values are multiplied by weights. Output layer Values are weighed and summed. TRAINING MLFN: TRAINING MLFN • Selecting how many hidden layers to use in the network. • Deciding how many neurons to use in each hidden layer. • Finding a globally optimal solution that avoids local minima. • Converging to an optimal solution in a reasonable period of time. • Validating the neural network to test for over fitting. BASIC BLOCK DIAGRAM: BASIC BLOCK DIAGRAM AT89C51: AT89C51 40 Pins with 32 pins for parallel ports. Extendable Memory, 4 parallel ports. 4 kb of ROM 128 bytes of RAM 32 I/O Address lines, 16 Interrupts. 4V to 6V Operating range. HARDWARE DETAILS: HARDWARE DETAILS Astable Multi vibrator generates square waves at 38.5 kHz. R = 370 k ohm, C = 100 pF. THEORY OF OPERATION: THEORY OF OPERATION Non linear output from detectors. Angle varies with distance and hence voltage. IR TRANSMITTER AND RECEIVER: IR TRANSMITTER AND RECEIVER From Multivibrator IR transmitter IR Receiver TYPE OF LEVELS: TYPE OF LEVELS System level Application level Function level Various Response Function : Various Response Function Jump Function Threshold Hyperbolic Tangent Logistic Function COMPARISIONBETWEEN ALGORITHM: COMPARISION BETWEEN ALGORITHM Goal Seeking Neuron: Goal Seeking Neuron Behavior Level Flexibility Decision making Response time GSN MODULE: GSN MODULE Boolean Expression Using GSN : Boolean Expression Using GSN Error vs Distance : Error vs Distance CHEMOTAXIS: CHEMOTAX I S Slide20: THANK YOU You do not have the permission to view this presentation. In order to view it, please contact the author of the presentation.
FINAL PRESENTATION chandru210486 Download Post to : URL : Related Presentations : Share Add to Flag Embed Email Send to Blogs and Networks Add to Channel Uploaded from authorPOINT Insert YouTube videos in PowerPont slides with aS Desktop Copy embed code: (To copy code, click on the text box) Embed: URL: Thumbnail: WordPress Embed Customize Embed The presentation is successfully added In Your Favorites. Views: 802 Category: Entertainment License: All Rights Reserved Like it (0) Dislike it (0) Added: August 17, 2007 This Presentation is Public Favorites: 0 Presentation Description No description available. Comments Posting comment... By: yogeshmanohar (22 month(s) ago) good Saving..... Post Reply Close Saving..... Edit Comment Close Premium member Presentation Transcript NEURAL NETWORK BASED ROBOT NAVIGATOR: NEURAL NETWORK BASED ROBOT NAVIGATOR BY, S.CHANDRASEKARAN H.JAIDEV S.KARTHIK OBJECTIVE: OBJECTIVE To navigate from one place to another by avoiding the obstacles automatically without any human intervention ANN : ANN A system Loosely modeled on human brain. Supervised learning. Needs both predictor and target variables The goal is to achieve the desired target. Unsupervised Learning. All variables are same. The goal is to look for patterns, clusters. MLFN DIAGRAM: MLFN DIAGRAM LAYERS OF MLFN: LAYERS OF MLFN Input layer Predictor variables. Hidden layer Values are multiplied by weights. Output layer Values are weighed and summed. TRAINING MLFN: TRAINING MLFN • Selecting how many hidden layers to use in the network. • Deciding how many neurons to use in each hidden layer. • Finding a globally optimal solution that avoids local minima. • Converging to an optimal solution in a reasonable period of time. • Validating the neural network to test for over fitting. BASIC BLOCK DIAGRAM: BASIC BLOCK DIAGRAM AT89C51: AT89C51 40 Pins with 32 pins for parallel ports. Extendable Memory, 4 parallel ports. 4 kb of ROM 128 bytes of RAM 32 I/O Address lines, 16 Interrupts. 4V to 6V Operating range. HARDWARE DETAILS: HARDWARE DETAILS Astable Multi vibrator generates square waves at 38.5 kHz. R = 370 k ohm, C = 100 pF. THEORY OF OPERATION: THEORY OF OPERATION Non linear output from detectors. Angle varies with distance and hence voltage. IR TRANSMITTER AND RECEIVER: IR TRANSMITTER AND RECEIVER From Multivibrator IR transmitter IR Receiver TYPE OF LEVELS: TYPE OF LEVELS System level Application level Function level Various Response Function : Various Response Function Jump Function Threshold Hyperbolic Tangent Logistic Function COMPARISIONBETWEEN ALGORITHM: COMPARISION BETWEEN ALGORITHM Goal Seeking Neuron: Goal Seeking Neuron Behavior Level Flexibility Decision making Response time GSN MODULE: GSN MODULE Boolean Expression Using GSN : Boolean Expression Using GSN Error vs Distance : Error vs Distance CHEMOTAXIS: CHEMOTAX I S Slide20: THANK YOU