Calculus is a big topic, but by and large, there are quite specific aspects of calculus that come into machine learning and in particular deep learning algorithms. This article is not intended to explain how and why things are as they are; rather it's my own personal cheat sheet for when I need to remember... Continue Reading →

# Data structures for deep learning

I recently completed the Udacity Deep Learning Nanodegree (highly worth doing by the way), which focuses on implementing a variety of deep learning architectures using PyTorch. At the outset, it's pretty fundamental to understand the data structures you'll be encountering as inputs to and outputs from your neural network architecture. What I noticed was that... Continue Reading →

# Poisson vs Exponential distributions

Related yet different, here's how... A quick note on the "preliminary terrors" of notation: e is Euler's number - you'll find the e on your calculator or the EXP() function in Excel The parameter is conventionally written as λ (pronounced lambda). Poisson Exponential Number of events that occur in an interval of time Time taken between 2... Continue Reading →

# Multivariate regression

So: with linear regression (aka simple linear regression) we have one feature which we are using to predict a dependent value (for example number of rooms as a predictor of house price). With multivariate regression (aka multiple linear regression) we simply have multiple features which could be used to predict that dependent value (for example... Continue Reading →

# Polynomial regression

Polynomial regression is a considered a special case of linear regression where higher order powers (x2, x3, etc.) of an independent variable are included. It's appropriate where your data may best be fitted to some sort of curve rather than a simple straight line. The polynomial module of numpy is easily used to explore fitting the best... Continue Reading →

# Co-variance, Correlation & Linear Regression

Typically we have 2 sets of values and we want to find out if these 2 sets of values are related, and if so how, and by how much? Could height be indicative of weight? Could hours of practice be related to how many errors are made in a mathematical test paper? Co-variance is a... Continue Reading →

# Linear algebra – check!

It's been a quiet few weeks on this blog as I spent nearly every spare moment wrestling with the challenges of linear algebra - and I'm in a celebratory mood this afternoon having passed everything within time! I must say that, having some tentative foundational skills, I'm left with 2 main feelings: A tremendous sense of... Continue Reading →

# A gem of a book :)

I've just bought this delightfully titled book: No bullshit guide to linear algebra by Ivan Savov. It's not necessarily easy learning everything you need to know about linear algebra for machine learning in 5 weeks (is that just me???) - so when I hit a bit of a brick wall in week 4 I went looking... Continue Reading →

# 3Blue1Brown – thank you!

This resource was just recommended via Coursera Mathematics for Machine Learning: Linear Algebra, and all I can say is WOW! Animated math: it's slick, it's professional, it's cute, it makes you smile - and it makes it all seem so obvious :). I can heartily recommend you take the time if you need help on Linear Algebra. In... Continue Reading →

It's started! The long-awaited Mathematics for Machine Learning: Linear Algebra - and it was worth waiting for - great lectures and coursework so far... So excited to be learning this stuff :).