https://chandrashaker.in/tags/design-choices/ Recent content in Design-Choices on Chandras Edu | AI, US Stocks, Courses & Jobs India Hugo en-in © 2026 Chandra Shaker · [Privacy Policy](/privacy-policy/) · [Disclaimer](/disclaimer/) · [Contact](/contact/) Mon, 01 Jun 2026 00:00:00 +0000 https://chandrashaker.in/courses/paiml/unit4/face-recognition/ Mon, 01 Jun 2026 00:00:00 +0000 https://chandrashaker.in/courses/paiml/unit4/face-recognition/ <h2 id="unit-4-navigation">Unit 4 Navigation</h2> <p><strong>← <a href="https://chandrashaker.in/courses/paiml/unit4/remarks-backpropagation/">Remarks on Backpropagation</a></strong>  |  <strong>Next → <a href="https://chandrashaker.in/courses/paiml/unit4/advanced-error-functions/">Advanced Topics: Error Functions</a></strong></p> <hr> <h2 id="47-face-recognition-with-backpropagation">4.7 Face Recognition with Backpropagation</h2> <p>This section walks through applying Backpropagation to a real learning task — recognising which direction a person is facing from a camera image. It illustrates the <strong>design decisions</strong> every ANN practitioner must make, and what the network actually learns internally.</p> <hr> <h2 id="471-the-task">4.7.1 The Task</h2> <h3 id="dataset">Dataset</h3> <table> <thead> <tr> <th>Property</th> <th>Detail</th> </tr> </thead> <tbody> <tr> <td>Total images</td> <td>624 greyscale images</td> </tr> <tr> <td>Subjects</td> <td>20 different people</td> </tr> <tr> <td>Images per person</td> <td>~32</td> </tr> <tr> <td>Image resolution</td> <td>120 × 128 pixels</td> </tr> <tr> <td>Pixel depth</td> <td>Greyscale, 0–255</td> </tr> </tbody> </table> <p><strong>Variations within the dataset:</strong></p>