Creating aesthetically pleasing pieces of art, including music, has been a long-term goal for artificial intelligence research. Despite recent successes of long-short term memory (LSTM) recurrent neural networks (RNNs) in sequential learning, LSTM neural networks have not, by themselves, been able to generate natural-sounding music conforming to music theory. To transcend this inadequacy, we put forward a novel method for music composition that combines the LSTM with Grammars motivated by music theory. The main tenets of music theory are encoded as grammar argumented (GA) filters on the training data, such that the machine can be trained to generate music inheriting the naturalness of human-composed pieces from the original dataset while adhering to the rules of music theory. Unlike previous approaches, pitches and durations are encoded as one semantic entity, which we refer to as note-level encoding. This allows easy implementation of music theory grammars, as well as closer emulation of the thinking pattern of a musician. Although the GA rules are applied to the training data and never directly to the LSTM music generation, our machine still composes music that possess high incidences of diatonic scale notes, small pitch intervals and chords, in deference to music theory.

We study the online estimation of the optimal policy of a Markov decision process (MDP). We propose a class of Stochastic Primal-Dual (SPD) methods which exploit the inherent minimax duality of Bellman equations. The SPD methods update a few coordinates of the value and policy estimates as a new state transition is observed. These methods use small storage and has low computational complexity per iteration. The SPD methods find an absolute-$\epsilon$-optimal policy, with high probability, using $\mathcal{O}\left(\frac{|\mathcal{S}|^4 |\mathcal{A}|^2\sigma^2 }{(1-\gamma)^6\epsilon^2} \right)$ iterations/samples for the infinite-horizon discounted-reward MDP and $\mathcal{O}\left(\frac{|\mathcal{S}|^4 |\mathcal{A}|^2H^6\sigma^2 }{\epsilon^2} \right)$ for the finite-horizon MDP.

One of the disadvantages of machine learning as a discipline is the lack of reasonable confidence intervals on a given prediction. There are all kinds of reasons you might want such a thing, but I think machine learning and data science practitioners are so drunk with newfound powers, they forget where such a thing might be useful. If you're really confident, for example, that someone will click on an ad, you probably want to serve one that pays a nice click through rate. If you have some kind of gambling engine, you want to bet more money on the predictions you are more confident of. Or if you're diagnosing an illness in a patient, it would be awfully nice to be able to tell the patient how certain you are of the diagnosis and what the confidence in the prognosis is. There are various ad hoc ways that people do this sort of thing.

Yet another research area in AI, neural networks, is inspired from the natural neural network of human nervous system. What are Artificial Neural Networks (ANNs)? The inventor of the first neurocomputer, Dr. Robert Hecht-Nielsen, defines a neural network as The idea of ANNs is based on the belief that working of human brain by making the right connections, can be imitated using silicon and wires as living neurons and dendrites. The human brain is composed of 100 billion nerve cells called neurons. They are connected to other thousand cells by Axons. Stimuli from external environment or inputs from sensory organs are accepted by dendrites. These inputs create electric impulses, which quickly travel through the neural network.

All the regression theory developed by statisticians over the last 200 years (related to the general linear model) is useless. Regression can be performed as accurately without statistical models, including the computation of confidence intervals (for estimates, predicted values or regression parameters). The non-statistical approach is also more robust than theory described in all statistics textbooks and taught in all statistical courses. It does not require Map-Reduce when data is really big, nor any matrix inversion, maximum likelihood estimation, or mathematical optimization (Newton algorithm). It is indeed incredibly simple, robust, easy to interpret, and easy to code (no statistical libraries required).

Like the course I just released on Hidden Markov Models, Recurrent Neural Networks are all about learning sequences - but whereas Markov Models are limited by the Markov assumption, Recurrent Neural Networks are not - and as a result, they are more expressive, and more powerful than anything we've seen on tasks that we haven't made progress on in decades. So what's going to be in this course and how will it build on the previous neural network courses and Hidden Markov Models? In the first section of the course we are going to add the concept of time to our neural networks. I'll introduce you to the Simple Recurrent Unit, also known as the Elman unit. We are going to revisit the XOR problem, but we're going to extend it so that it becomes the parity problem - you'll see that regular feedforward neural networks will have trouble solving this problem but recurrent networks will work because the key is to treat the input as a sequence.

We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We show a convergence rate of $O(1/k)$ with the constant term depending on the number of agents and the topology of the network. Moreover, we show almost sure convergence to the optimal solution of the estimation problem for the general case of time-varying directed graphs.

Heart diseases constitute a global health burden, and the problem is exacerbated by the error-prone nature of listening to and interpreting heart sounds. This motivates the development of automated classification to screen for abnormal heart sounds. Existing machine learning-based systems achieve accurate classification of heart sound recordings but rely on expert features that have not been thoroughly evaluated on noisy recordings. Here we propose a segmental convolutional neural network architecture that achieves automatic feature learning from noisy heart sound recordings. Our experiments show that our best model, trained on noisy recording segments acquired with an existing hidden semi-markov model-based approach, attains a classification accuracy of 87.5% on the 2016 PhysioNet/CinC Challenge dataset, compared to the 84.6% accuracy of the state-of-the-art statistical classifier trained and evaluated on the same dataset. Our results indicate the potential of using neural network-based methods to increase the accuracy of automated classification of heart sound recordings for improved screening of heart diseases.

This revision has corrected derivations, new R/JAGS code, and new diagrams.] Overview "Captain, the prior probability of this character dying and leaving the show is infinitesimal." A primary example of Bayes' rule is for disease diagnosis (or illicit drug screening). The example is invoked routinely to explain the importance of prior probabilities. Here's one version of it: Suppose a diagnostic test has a 97% detection rate and a 5% false alarm rate.

Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks. Our learning algorithm simultaneously learns a compiled inference network and the generative model, leveraging a structured variational approximation parameterized by recurrent neural networks to mimic the posterior distribution. We apply the learning algorithm to both synthetic and real-world datasets, demonstrating its scalability and versatility. We find that using the structured approximation to the posterior results in models with significantly higher held-out likelihood.