| layout | title | nav_order |
|---|---|---|
default |
Outline |
1 |
In this workshop, participants will dive into the fascinating world of neural networks. Neural networks have emerged as powerful models for solving complex and nonlinear problems. This workshop begins with an introduction to neural networks, covering their architecture, activation functions, and training algorithms. Participants will gain insights into how neural networks can effectively capture and learn complex patterns in images, making them ideal for tasks like recognizing digits. They will also learn about the importance of preprocessing techniques and streamlining the preprocessing, training, and evaluation steps through pipelines. By the end of this workshop, participants will have a solid foundation in neural networks and the ability to build robust pipelines using Scikit-learn.
In this workshop, we will use cloud-based platforms, so you don’t need to have Python installed. Please make sure that you have a Google Colaboratory (https://colab.research.google.com/) account. This workshop will involve hands-on exercises that require the use of programming tools and libraries commonly used in machine learning, such as Python and Scikit-learn. As such, prior familiarity with Python programming is recommended for participants to fully benefit from the practical component of the workshop. Sign up for other Machine Learning workshops in this series.
At the end of this workshop, you will be able to:
- Understand neural networks, and their applications in machine learning.
- Train neural network models for real-world datasets.
- Interpret and analyze neural network model results.
| 0:00 - 0:05 | Welcome and using Zoom|
| 0:05 - 0:30 | About Neural Networks |
| 0:30 - 1:20 | Hands-on with Jupyter Notebook|
| 1:20 - 1:30 | Wrap-up and Discussion|
| 1:30 - 2:00 | Optional Q&A|
Find the workshop slides below or open it in a new tab:
Your browser does not support iframes.
</iframe>Workshop 1- Regression: Click here
Workshop 2- Classification & Clustering: Click here
- Colab Notebook:
