The main Machine Learning algorithms [white board]
Predicting house prices using Linear Regression and Gradient Descent
Detecting spam emails using Naive Bayes Algorithm
Recommending Apps based on Decision Trees [animation]
Finding the best location for a shop based on K-means clustering or Hierarchical Clustering
Deciding to accept students at a university based on Logistic Regression and Gradient Descent with Log-loss function
When a line is not enough … or the kernel trick of Support Vector Machines
Advance Analytics with Deep Learning
Hands-on the Linear Perceptron and the linear classification problems it can solve [screenshot]
Hands-on the Linear Perceptron and the simple non-linear classification problems it can solve [screenshot]
Hands-on Deep Learning and the complex non-linear classification problems it can solve using sigmoid [screenshot], ReLU [screenshot] and deep NN [screenshot]
Demo: how Keras + Tensorflow can classify correctly the MNIST Digits Dataset
Demo: how Keras + Tensorflow can understand images using Inception V3 model
Understanding Training using Gradient Descent and Back Propagation
Introducing non-linearity: from Sigmoid to ReLU
Hands-on Neural Network with Keras building a “Dense Feed-Forward Shallow” Network to predict the house price on the Boston Housing dataset.
More on Neural Networks with Keras: Data Normalization (e.g., standard scaler), Custom Metrics, Validation data, callbacks (e.g., check pointing and early stopping), and Saving Models
Hands-on Neural Network with Keras optimizing the “Dense Feed-Forward Shallow” Network built in previous hands-on to predict the house price on the Boston Housing dataset.
The datasets available: people flows from counting sensors, people presence and demographics from mobile telecom data, free parking, weather, and social media
Learning to formulate an Urban Data Science problem
Setting a Urban Data Science problem
Using methods and techniques learnt in previous days to solve the set problem
if you cannot install docker, you can try Docker for Beginners (registration is required)
From SQL to noSQL and back to newSQL [22 (pm) / 27 (am) / 29 (am) 11.2018 ]
Gitter channel used during the lecture. It contains all the raw examples.
Brainstorm on which are the requirements of a Database Management System (DBMS), how Relational DBMS address those needs since the ’90s and whether a different approach was possible in the 2000s and is mandatory in the 2010s [whiteboard]
A running example we will use across the lecture [Entity Relationship diagram, example data]
