Getting Started to ML
Table of contents
Getting Started to ML
For the first lab session, we will explore the various components necessary to implement and train machine learning models. We expect everyone to have basic programming experience in Python, as the lab assignments and lessons will be conducted in Python. If you do not have prior experience, there are numerous introductory Python videos available online, and we are here to help if you need further assistance.
Setting up Google Colab
In the lab assignments and lessons, you will work with a Python notebook file (.ipynb) and will need a machine with GPU support to train the models. If you have a personal computer with GPU support, you can install CUDA drivers to run the deep learning framework. However, the most convenient solution for everyone is to use Google Colab for running your notebook files, as it saves installation and setup time. To use Colab, go to this link, create a new notebook file, or upload an existing one. Don’t forget to sign in to your google account. You are now ready to run your assignments. You can also check out the following video on how to setup a notebook file in Google colab.
Numpy
Numpy is a fundamental library used for scientific computation with python. It provides support for large multidimensional arrays and matrices, along with a collection of mathematical functions to operate on these arrays efficiently. Check out the following video on basics to Numpy.
Matplotlib
Matplotlib is a python library used for data analysis, plotting and visualization in machine learning. Below you can find a video on how to plot a simple function using Matplotlib.
Keras
As our deep learning framework, we will use Keras. You can find more information about how to use keras in their official documentation, and we will go through some of them during the lab lesson. However, for a quick introduction, check out the following video on basics of deep learning using Keras.
