Learning in Brains and Machines (4): Episodic and Interactive Memory

Learning in Brains and Machines (4): Episodic and Interactive Memory
· Read in · 2080 words · All posts in series  · memory, like yours, exerts a powerful influence over my interaction with the world. It is reconstructive and evocative; I can easily form an image of hot December days in the South African summer, and remember my first time—it was morning on an Easter Sunday in April a few years ago—that I saw and felt snow. My ...

Learning in Brains and Machines (2): The Dogma of Sparsity 1

Learning in Brains and Machines (2): The Dogma of Sparsity
· Read in · 1700 words · collected posts · functioning of our brains, much like the intrigue of a political drama, is a neuronal house-of-cards. The halls of cognitive power are run by recurring alliances of neurons that deliberately conspire to control information processing and decision making. 'Suspicious coincidences' in neural activation—as the celebrated neuroscientist Horace Barlow observed—are abound; transparency in neural ...

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 ...

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 ...