Skip to content

Latest commit

 

History

History
65 lines (34 loc) · 4.61 KB

README.md

File metadata and controls

65 lines (34 loc) · 4.61 KB
Raw

AI DOJO Machine Learning Bootcamp

This is the repository for The Machine Learning Bootcamp published by AI DOJO. It contains all the Bootcamp code with supporting project files necessary to work through the code.

Note: to access our previous Bootcamp resources, please refer to the below link

Requirements and Setup

We recommend to use Colab, you will find Colab icon in the top of all AI DOJO code. If you want to use your own pc please follow the instructions below:

  1. Install Python on Windows/Mac.
  2. Install pip for Windows/Mac/Linux.
  3. Make sure to install the necessary python packages for the Bootcamp from the requirements.txt file.
  4. Donwload the code editer, we recommend vscode

About The AI DOJO Machine Learning Bootcamp

With expert guidance and real-world examples the AI DOJO Machine Learning Bootcamp will walk you through the process of building, training, and model evaluation of your Machine Learning and Deep Learning algorithms by showing you how to leverage TensorFlow flexibility. The AI DOJO Machine Learning Bootcamp will teach you all the skills you need to use Machine Learning & Deep Learning in the right way.

What You Will Learn

  • WEEK 01 – INTRODUCTION TO PYTHON

    Review of the Python programming language that covers basic syntax, variables, arithmetic operations, control flow, functions, classes, and built-in Python modules. All applied using Google Colab.

  • WEEK 02 – DATA SCIENCE LIBRARIES

    Introduction to 3rd party Python libraries that are used to data science tasks like NumPy for working with numerical tensors and matrices, Pandas for working with tabular data, and Matplotlib for data visualization.

  • WEEK 03 – MACHINE LEARNING ALGORITHMS

    Introduction to Scikit Learn, a machine learning library that covers a wide range of ML tasks like preprocessing and preparing data to defining, training, and tuning different machine learning algorithms to evaluating their performance and measure their accuracy.

  • WEEK 04 – DEEP LEARNING ALGORITHMS

    Introduction to Deep Learning using TensorFlow framework and the building blocks that go into training deep learning models including Neural Network and its components like activation functions, loss function, optimizers, evaluation metrics, and data pipelines.

  • WEEK 05 – COMPUTER VISION

    Introduction to Convolutional Neural Networks (CNNs) using TensorFlow, images preprocessing and data pipelines, using pretrained models for Transfer Learning, and exploring different CNN architectures like ResNet, Inception, and more.

  • WEEK 06 – COMPUTER VISION APPLICATIONS

    Build advanced computer vision-powered applications beyond basic image classification including object detection, semantic segmentation, and more advanced CNN training techniques.

  • WEEK 07 – SEQUENCE MODELLING

    Introduction to Recurrent Neural Networks (RNNs) and its variations like GRUs and LSTMs which are used to sequential data like text and time series. We’ll use these Neural Networks to perform tasks like sentiment analysis and text generation.

  • WEEK 08 – ADVANCED SEQUENCE APPLICATIONS

    Introduction to more advanced RNN-based architectures like Autoencoders. We’ll also build more sophisticated applications like Neural Machine Translation and Forecasting using RNN-based models.

  • WEEK 09 – MORE ADVANCED DL APPLICATIONS

    We’ll explore more Deep Learning applications like Recommendation Systems. We’ll also introduce platforms like Gradio that helps us quickly build interactive demos for our Deep Learning models.

  • WEEK 10 – MODEL DEPLOYMENT with TENSORFLOW

    We’ll learn how to deploy and serve our trained models across different platforms including via REST APIs and mobile applications using TensorFlow Lite.