> For the complete documentation index, see [llms.txt](https://techacademy.gitbook.io/ai-track-wise24_25/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://techacademy.gitbook.io/ai-track-wise24_25/section-3-neural-networks/exercise-implementing-gradient-descent.md).

# Exercise - Implementing Gradient Descent

{% file src="/files/R62LQEBLYvG5P8KLSQeD" %}

In this notebook you will optimize a linear function of the form $a\*x$ that has only one parameter. The goal is that your model learns based on data which value the parameter should have to match the true function.

<figure><img src="/files/hSBRb3JiL9kHE6oSmzVQ" alt=""><figcaption><p>The green function is the true function, the orange one is the model. Your task will be to optimize the model with the gradient descent algorithm so that it comes closer to the true function.</p></figcaption></figure>