Setup a basic Python environment, create virtual environments and learn how to install Python packages.

Linux

Learn the fundamentals about a Linux environment – how to navigate through the filesystem and modify files.

Git

Learn to keep track of changes and iterations using git source control from your terminal.

NumPy

Use the Python and NumPy to navigate through data sources

Intro. to data Visualization

Learn how to plot and visualize data by using Python plotting libraries such as matplotlib and seaborn

Learn about some of the most common data formats, like CSV, XML and JSON files and how to handle them.

Pandas

Use Pandas to read, clean, parse, and plot data using functions such as Boolean, indexing, math series, joins, and others

Web Scraping

Learn to scrape website data using popular scraping tools

Use scikit learn and stats models to run linear and logistic regression models and learn to evaluate model fit

Gradient Descent

Dive into the math and theory of how gradient descent helps to optimize loss function for regression models

Feature Selection

Use feature selection to deepen your knowledge of study design and model evaluation.

Feature engineering & pre-processing

Learn about different the possible ways of encoding the data features and their advantages and disadvantages.

Learn about the fundamentals of Artificial Neural Networks, – how do they work, their advantages and how to train them.

Backpropagation and Optimizers

Learn how the backpropagation algorithm works and is able to train neural networks. See what different optimizers are available and their advantages in the training process.

Regularization

Learn how to apply regularization in order to avoid problems in the training such as overfitting.

Introduction to TensorFlow

Build simple artificial neural network models with TensorFlow, a differentiable programming framework

Keras

Introduction to the Keras framework for Python and how to use it to build neural network models

Clustering

Learn how to use clustering algorithms in order to visualize and interpret classification tasks.

Dive into the world of image classification problems by using Deep Convolutional Neural Networks. (D-CNNs)

Data Augmentation

Understand how data augmentation can be used to help models to learn better, and to artificially increase the size of the original dataset.

Adversarial examples

Learn how adversarial examples can be used to trick a neural network into outputting wrong results and how to deal with this problem.

Learn the basic concepts and tasks of natural language processing (NLP)

Recurrent Neural Networks (RNNs)

Use RNNs in order to model sequences of data

Long Short-Term Memory (LSTM)

Learn how LSTMs solve the common problems of RNNs and how can they used to perform machine learning tasks on large sequences

Time series analysis

Analyze and model time series data using LSTM networks.

Learn how to create a simple REST API to deploy your machine learning models

Docker

Use Docker to create isolated containers with all the required dependencies and

AWS

Learn the basics of the Amazon cloud infrastructure and how it can be used to train and deploy machine learning models.