Thursday, February 1, 2018

Deep Learning - Introduction and Bibliography

Deep learning is a form of machine learning for nonlinear high dimensional data reduction
and prediction.

Using  Bayesian probabilistic perspective in deep learning provides a number of advantages. Specifically statistical interpretation and properties, more efficient algorithms for optimisation and
hyper-parameter tuning, and an explanation of predictive performance. Traditional high dimensional
statistical techniques; principal component analysis (PCA), partial least squares
(PLS), reduced rank regression (RRR), projection pursuit regression (PPR) are shallow learners. Their deep learning counterparts exploit multiple layers of of data reduction which leads to performance gains. Stochastic gradient descent (SGD) training and optimisation
and Dropout (DO) provides model and variable selection. Bayesian regularization
is central to finding networks and provides a framework for optimal bias-variance trade-off
to achieve good out-of sample performance.

To illustrate the use of bayesian perspective,  an analysis of first time international bookings on Airbnb. is presented in the paper.

Deep Learning Introduction


How to get started with Deep Learning for Data Science?

-1. Learn Python and R ;)

0. Andrew Ng and Coursera


1. Siraj Raval: YouTube channel. Specifically this playlists:

- The Math of Intelligence:

- Intro to Deep Learning:

2. François Chollet's book: Deep Learning with Python (and R soon):


3. IBM Cognitive Class:


4. Medium blogs:


5. DataCamp:


Info collected from a Linkedin Post


Updated 2 February 2018
5 June 2017

No comments:

Post a Comment