[Recommended][HR-r] as containing a good introduction to Bayesian statistics.

[HN-r]: http://news.ycombinator.com/item?id=3793948

"... The occurrence and duration of latching dynamics is found through simulations to depend critically on the strength of local attractor states, expressed in the Potts model by a parameter w. Here we describe with simulations and then analytically the boundaries between distinct phases of no latching, of transient and sustained latching, deriving a phase diagram in the plane w-T, where T parametrizes thermal noise effects. Implications for real cortical dynamics are briefly reviewed in the conclusions."

In the 1980's, new learning algorithms for neural networks promised to solve difficult classification tasks, like speech or object recognition, by learning many layers of non-linear features. The results were disappointing for two reasons: There was never enough labeled data to learn millions of complicated features and the learning was much too slow in deep neural networks with many layers of features. These problems can now be overcome by learning one layer of features at a time and by changing the goal of learning. Instead of trying to predict the labels, the learning algorithm tries to create a generative model that produces data which looks just like the unlabeled training data. These new neural networks outperform other machine learning methods when labeled data is scarce but unlabeled data is plentiful. An application to very fast document retrieval will be described.

Fast Artificial Neural Network Library is a free open source neural network library, which implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks. Cross-platform execution in both fixed and floating point are supported. It includes a framework for easy handling of training data sets. It is easy to use, versatile, well documented, and fast. Bindings to more than 15 programming languages are available. An easy to read introduction article and a reference manual accompanies the library with examples and recommendations on how to use the library. Several graphical user interfaces are also available for the library.

Over the weekend I was struck with the realization that I don’t know how to use neural networks in practice, damn it. Even though a few months ago I realized what neural networks are, even though I’ve tried implementing them, even though I’ve used them in a class setting … How the hell do you use these things in real life!? Implement from scratch? … no that can’t be it.

The following introduction is to allow viewers to understand the basic concepts and practical implementation of neural nets towards a financial time series. I will not go too deep into detail about the mathematics behind the neural net at the moment. My goal is to get you to understand practical details about how to actually implement a neural net using simple tools and models. We will start with a simple model to understand a basic time series. The time series waveform is a simple sine wave with the period set to 30 days. It is implemented in excel as a source file to be processed in any Machine Learning capable software.

"Autoencoders are unsupervised machine learning circuits whose learning goal is to minimize a distortion measure between inputs and outputs. Linear autoencoders can be defined over any field and only real-valued linear autoencoder have been studied so far. Here we study complex-valued linear autoencoders where the components of the training vectors and adjustable matrices are defined over the complex field with the $L_2$ norm. We provide simpler and more general proofs that unify the real-valued and complex-valued cases, showing that in both cases the landscape of the error function is invariant under certain groups of transformations. The landscape has no local minima, a family of global minima associated with Principal Component Analysis, and many families of saddle points associated with orthogonal projections onto sub-space spanned by sub-optimal subsets of eigenvectors of the covariance matrix. The theory yields several iterative, convergent, learning algorithms, a clear understanding of the generalization properties of the trained autoencoders, and can equally be applied to the hetero-associative case when external targets are provided. Partial results on deep architecture as well as the differential geometry of autoencoders are also presented. The general framework described here is useful to classify autoencoders and identify general common properties that ought to be investigated for each class, illuminating some of the connections between information theory, unsupervised learning, clustering, Hebbian learning, and auto encoders."

Best Practices for Convolutional Neural Networks
Applied to Visual Document Analysis