Talk: Building Machines that Imagine and Reason 2

Talk: Building Machines that Imagine and Reason
I am excited to be one the speakers at this year's Deep Learning Summer School in Montreal on the 6th August 2016. Slides can be found here: slides link. And the abstract is below. Building Machines that Imagine and Reason: Principles and Applications of Deep Generative Models Deep generative models provide a solution to the problem of unsupervised ...

Bayesian Reasoning and Deep Learning 4

Bayesian Reasoning and Deep Learning
I gave a talk entitled 'Bayesian Reasoning and Deep Learning' recently. Here is the abstract and the slides for interest. Slides Bayesian Reasoning and Deep Learning Abstract Deep learning and Bayesian machine learning are currently two of the most active areas of machine learning research. Deep learning provides a powerful class of models and an ...

A Statistical View of Deep Learning (VI): What is Deep? 6

A Statistical View of Deep Learning (VI): What is Deep?
Throughout this series, we have discussed deep networks by examining prototypical instances of these models, e.g., deep feed-forward networks, deep auto-encoders, deep generative models, but have not yet interrogated the key word we have been using. We have not posed the question what does 'deep' mean, and what makes a model deep. There is little in way of ...

A Statistical View of Deep Learning (V): Generalisation and Regularisation 1

A Statistical View of Deep Learning (V): Generalisation and Regularisation
We now routinely build complex, highly-parameterised models in an effort to address the complexities of modern data sets. We design our models so that they have enough 'capacity', and this is now second nature to us using the layer-wise design principles of deep learning. But some problems continue to affect us, those that we encountered even in the low-data ...

A Statistical View of Deep Learning (IV): Recurrent Nets and Dynamical Systems 3

A Statistical View of Deep Learning (IV): Recurrent Nets and Dynamical Systems
Recurrent neural networks (RNNs) are now established as one of the key tools in the machine learning toolbox for handling large-scale sequence data. The ability to specify highly powerful models, advances in stochastic gradient descent, the availability of large volumes of data, and large-scale computing infrastructure, now allows us to apply RNNs in the most creative ...

A Statistical View of Deep Learning (II): Auto-encoders and Free Energy 7

A Statistical View of Deep Learning (II): Auto-encoders and Free Energy
With the success of discriminative modelling using deep feedforward neural networks (or using an alternative statistical lens, recursive generalised linear models) in numerous industrial applications, there is an increased drive to produce similar outcomes with unsupervised learning. In this post, I'd like to explore the connections between denoising auto-encoders as a leading approach for unsupervised learning in deep learning, and density estimation ...

Variational Inference: Tricks of the Trade 5

Variational Inference: Tricks of the Trade
The NIPS 2014 Workshop on Advances in Variational Inference was abuzz with new methods and ideas for scalable approximate inference. The concluding event of the workshop was a lively debate with David Blei, Neil Lawrence, Zoubin Ghahramani, Shinichi Nakajima and Matthias Seeger on the history, trends and open questions in variational inference. One of the questions posed to our panel ...

Bayesian sparsity using spike-and-slab priors

I recently received some queries on our paper: S. Mohamed, K. Heller and Z. Ghahramani. Bayesian and L1 Approaches for Sparse Unsupervised Learning. International Conference on Machine Learning (ICML), June 2012 . The questions were very good and I thought it would be useful to post these for future reference. The paper looked at Bayesian ...