Collection Updated a year ago

A non practitioner guide to machine learning

Introductory guide to machine learning with Keras and Tensorflow



Intro and Setup

Getting Started With Machine Learning (Non practitioner guide)

In the recent years, machine learning has made a comeback into everybodys conversations. From the classrooms in Stanford or MIT, to movies like HER or Ex-Machina, AI is not just permeating all our lives but also our imagination. But as a developer, how can you start dipping your toes in AI, understand it and possibly change the world with it? Thats what this guide is for, a quick intro from a non-practitioner for non-practitioners :) Well install the basic tools required, download some datasets

Davide Scalzo

1 min read

07 Nov 19

Installing Anaconda, Python3 and Tensorflow

First thing first, heres a list of the things we need to start playing around with some data: - Python - Anaconda - Jupiter Notebook - A bunch of data manipulation tools like Numpy, Scikit etc.. Luckily for us, the Anaconda distribution includes all of them, head on to and follow the instructions. Anaconda homepage On linux is as easy as downloading the file, opening the terminal and type ~$ bash Anaconda3- from the folder you downloaded th

Davide Scalzo

3 min read

22 Oct 19

Supervised Learning

Regression with Python, Keras and Tensorflow

In this tutorial we are going to do a quick and dirty estimation of house prices based on a dataset from a Kaggle competition. Kaggle is the leading data science competition platform and provides a lot of datasets you can use to improve your skills. For simplicitys sake, we will build a simple model to get us started and we will explore how to improve it in later articles. Before we start, download the following file, which contains the training dataset, the test dataset and a sample submission

Davide Scalzo

6 min read

22 Oct 19

Predict cryptocurrency prices with Tensorflow as binary classification problem

Introduction In this tutorial well go through the prototype for a neural network which will allow us to estimate cryptocurrency prices in the future, as a binary classification problem, using Keras and Tensorflow as the our main clarvoyance tools. While it is most likely not the best way to approach the problem (after all investment banks invest billions in developing such algorithms), if we can get it right more than 55% of the times, we are in the money! What well be doing Download data using

Davide Scalzo

15 min read

22 Oct 19

Multi-class classification example with Convolutional Neural Network in Keras and Tensorflow

In the previous articles, we have looked at a regression problem and a binary classification problem. Lets now look at another common supervised learning problem, multi-class classification. The staple training exercise for multi-class classification is the MNIST dataset, a set of handwritten roman numerals, while particularly useful, we can spice it up a little and use the Kannada MNIST dataset available on Kaggle. The Kannada language is spoken in southern regions of India, by around 45 millio

Davide Scalzo

5 min read

09 Oct 19