Deep Learning lectures
Here is the material for a course of two-weeks I will be giving in a Master of Data Science and AI
This is part of a series of other lectures modules on
- Introduction to Data Science 🧮
- Statistical Learning 📈
- Time Series ⌛
- Computer Vision Hands-On 🕶️
- Recommender Systems 🚀
Content of lectures
You can find the list of the arguments and some relevant material here.
Install requirements
As usual, it is advisable to create a virtual environment to isolate dependencies. One can follow this guide and the suitable section according to the OS.
Once the virtual environment has been set up, one has to run the following instruction from a command line
pip install -r requirements.txt
This installs all the packages the code in this repository needs.
Mac M1 processors
For new Apple M1 processors, there is a different requirement file. So set the virtual environment and then the command to execute is
pip install -r requirements-macm1.txt
This installs all the packages the code in this repository needs.
Interact with notebooks
Binder
You can use Binder, to interact with notebooks and play with the code and the exercises.
DeepNote
Alternatively, you can work on these notebooks in another online workspace called Deepnote. This allows you to play around with the code and access the assignments from your browser.
Run lectures in a Docker container
Another option to run all these lectures locally is to build the corresponding Docker Image. A nice introduction to Docker containers can be found here.
We tried to modularise everything to make all the building and execution procedure as simple as possible. To run a jupyter environment with all dependencies installed and notebooks ready to be executed it is sufficient to open your favourite terminal and run
make
The Makefile will take care of building and executing the docker image. Then a jupyter server will be running at http://localhost/8888.
Your lecturer 👨🏫
Oscar de Felice
I am a theoretical physicist, a passionate programmer and an AI curious.
I write medium articles (with very little amount of regularity), you can read them here. I also have a github profile where I store my personal open-source projects.
Questions
If you have any question, doubt or if you find mistakes, please open an issue or drop me an email.
Buy me a coffee ☕️
If you like these lectures, consider to buy me a coffee ☕️ !
