https://chandrashaker.in/tags/delta-rule/ Recent content in Delta-Rule 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/perceptrons/ Mon, 01 Jun 2026 00:00:00 +0000 https://chandrashaker.in/courses/paiml/unit4/perceptrons/ <h2 id="unit-4-navigation">Unit 4 Navigation</h2> <p><strong>← <a href="https://chandrashaker.in/courses/paiml/unit4/appropriate-problems/">Appropriate Problems for NN Learning</a></strong>  |  <strong>Next → <a href="https://chandrashaker.in/courses/paiml/unit4/backpropagation/">Multilayer Networks and Backpropagation</a></strong></p> <hr> <h2 id="44-perceptrons">4.4 Perceptrons</h2> <h3 id="what-is-a-perceptron">What Is a Perceptron?</h3> <p>A <strong>perceptron</strong> is a single computational unit that takes a vector of real-valued inputs x₁, x₂, …, xₙ, computes their weighted sum, and outputs <strong>+1</strong> if the sum exceeds a threshold, <strong>-1</strong> otherwise.</p> <pre tabindex="0"><code>Output o(x₁, ..., xₙ): = +1 if w₀ + w₁x₁ + w₂x₂ + ... + wₙxₙ &gt; 0 = -1 otherwise </code></pre><p>Each wᵢ is a real-valued <strong>weight</strong>. The quantity <strong>−w₀</strong> is the <strong>threshold</strong> that the weighted sum must exceed.</p>