Rise of the MachinesJack Concanon

“A Field of study that gives computers the ability to learn without being explicitly programmed

- Arthur Samuel

  “A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at

tasks in T, as measured by P, improves with experience E

- Tom M. Mitchell

Can Machines Think?

Can machines do what we do?

Can they pretend?

How much help do they need?

Why Now?

http://internet-map.net

Supervised Learning Requires labelled training

examples Function approximation Based on an input vector

you should receive an expected output

Linear regression is the simplest

Line of best fit is a valid tool for prediction

Unsupervised Learning

Unclassified data

Finding hidden structures

Clustering

Data mining

Linear Regression Example

Neural Networks

Neural Network Visualisation

Example – Cat or Hat?

Thanks for Listening!• How much data is made each minute? -

http://www.visualnews.com/2012/06/19/how-much-data-created-every-minute/

• What does a hidden layer do? - https://stats.stackexchange.com/questions/63152/what-does-the-hidden-layer-in-a-neural-network-compute#63163

• Animating neural networks using R - http://beckmw.wordpress.com/2013/03/19/animating-neural-networks-from-the-nnet-package/

• Google research document on identifying high level features from images of humans and cats – https://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/archive/unsupervised_icml2012.pdf

• Google research documents on machine learning - http://research.google.com/pubs/ArtificialIntelligenceandMachineLearning.html

• Coursera Machine Learning - https://www.coursera.org/course/ml