Module 4: Deep Learning Using Neural Networks
In this lesson, we will learn the basics of deep learning based on artificial neural networks, or simply neural networks (NN). As a specific subset of machine learning (ML), NN has proven to achieve impressive accuracy over traditional ML methods. We will use TensorFlow and Keras library to build and train NN models relevant to mobile phone cybersecurity applications. Many of today’s AI-based systems such as speech input processing (found on your smart phones, Google Home, Alexa, among others), image recognition, digital assistants, and self-driving cars are powered by highly complex NN models.
Please check out our Neural Networks lesson at the following page:
Workshop Resources (Workshop Series 2020-2021)
Presentation Slides
Presentation slides (PDF) by Kazi Aminul Islam
Jupyter Notebooks
The list of notebooks below reflects the actual sequence of notebooks taken during ML session of the 2020-2021 workshop series.
(To download the notebook and the hands-on files, please right-click on the links below and select “Save Link As…” or a similar menu)
- Session 1: Binary Classification with Keras - (html)
- Session 2: Classifying Smartphone Apps with Keras - (html)
(The HTML files were provided for convenient web viewing.)
Hands-on Files
- Sherlock hands-on files for ML and NN lessons, except the large files (table of contents) – This also contains the Jupyter notebooks above
- Sherlock large dataset:
sherlock_2apps(table of contents) - Sherlock large dataset:
sherlock_18apps(table of contents)
The hands-on files are packed in ZIP format. The three ZIP files above are mandatory. To reconstitute: Unzip all the files, preserving the paths, into the same destination directory.