Skip to main content Skip to navigation

Learning Deep Learning

Brute force your PhD, MSc, or final year undergraduate project by throwing a deep learning algorithm at it - easy, problem solved! This could not be better summarised by a machine learning researcher Ferenc Huszar at twitter - “The reason deep learning made such a splash is the very fact that it allows us to phrase several previously impossible learning problems as empirical loss minimisation via gradient descent, a conceptually super simple thing. Deep networks deal with natural signals we previously had no easy ways of dealing with: images, video, human language, speech, sound. But almost whatever you do in deep learning, at the end of the day it becomes super simple: you combine a couple basic building blocks and ideas (convolution, pooling, recurrence), you can do it without overthinking it, if you have enough data the network will figure it out.” In these tutorials we will get up to speed with the simple building blocks of deep learning, and how one could optimise them for a task of your choice!

Ferenc H (2016) Deep Learning is Easy - Learn Something Harder. In: inFERENCe. Accessed 6 Apr 2019