End-to-end automatic speech recognition system implemented in TensorFlow. If you want to replace feed dict operation with Tensorflow multi-thread and fifoqueue input pipeline, you can refer to my repo TensorFlow-Input-Pipeline for more example codes. My own practices prove that fifoqueue input pipeline would improve the training speed in some time. If you want to look the history of speech recognition, I have collected the significant papers since 1981 in the ASR field. I will update it every week to add new papers, including speech recognition, speech synthesis and language modelling.

In this paper we use Gaussian Process (GP) regression to propose a novel approach for predicting volatility of financial returns by forecasting the envelopes of the time series. We provide a direct comparison of their performance to traditional approaches such as GARCH. We compare the forecasting power of three approaches: GP regression on the absolute and squared returns; regression on the envelope of the returns and the absolute returns; and regression on the envelope of the negative and positive returns separately. We use a maximum a posteriori estimate with a Gaussian prior to determine our hyperparameters. We also test the effect of hyperparameter updating at each forecasting step. We use our approaches to forecast out-of-sample volatility of four currency pairs over a 2 year period, at half-hourly intervals. From three kernels, we select the kernel giving the best performance for our data. We use two published accuracy measures and four statistical loss functions to evaluate the forecasting ability of GARCH vs GPs. In mean squared error the GP's perform 20% better than a random walk model, and 50% better than GARCH for the same data.

Machine Learning is getting a lot more air time these days but are we actually sure what it is? It gives computers the ability to learn without being explicitly programmed" (Arthur Samuel, 1959). This is an old quote but it has held the test of time. But,how can computers "learn" – have we really reached the age of artificial intelligence where they will take over the world and make humans redundant? Let's explore the core of the definition: the ability to learn What this really means is there are a set of algorithms that, rather than simply following a static set of program instructions, they can make data driven predictions, or decisions through building a model. Supervised learning – The computer is presented with example inputs (training data) and their desired outputs, given by a "teacher", and the goal is to learn a general rule that maps inputs to outputs. The "easiest" example of supervised learning is a decision tree – this uses a tree-like graph or model of decisions and ...

We consider the inference of the structure of an undirected graphical model in an exact Bayesian framework. More specifically we aim at achieving the inference with close-form posteriors, avoiding any sampling step. This task would be intractable without any restriction on the considered graphs, so we limit our exploration to mixtures of spanning trees. We consider the inference of the structure of an undirected graphical model in a Bayesian framework. To avoid convergence issues and highly demanding Monte Carlo sampling, we focus on exact inference. More specifically we aim at achieving the inference with close-form posteriors, avoiding any sampling step. To this aim, we restrict the set of considered graphs to mixtures of spanning trees. We investigate under which conditions on the priors - on both tree structures and parameters - exact Bayesian inference can be achieved. Under these conditions, we derive a fast an exact algorithm to compute the posterior probability for an edge to belong to {the tree model} using an algebraic result called the Matrix-Tree theorem. We show that the assumption we have made does not prevent our approach to perform well on synthetic and flow cytometry data.

We consider the nonlinear Kalman filtering problem using Kullback-Leibler (KL) and $\alpha$-divergence measures as optimization criteria. Unlike linear Kalman filters, nonlinear Kalman filters do not have closed form Gaussian posteriors because of a lack of conjugacy due to the nonlinearity in the likelihood. In this paper we propose novel algorithms to optimize the forward and reverse forms of the KL divergence, as well as the alpha-divergence which contains these two as limiting cases. Unlike previous approaches, our algorithms do not make approximations to the divergences being optimized, but use Monte Carlo integration techniques to derive unbiased algorithms for direct optimization. We assess performance on radar and sensor tracking, and options pricing problems, showing general improvement over the UKF and EKF, as well as competitive performance with particle filtering.

Research Scientist – Bayesian Machine Learning Location: Cambridge - United Kingdom The Schlumberger Gould Research Centre offers a stimulating research environment with real-world problems that push the limits of scientific knowledge. We are committed to be at the leading edge of science and to incorporate new emerging technologies in Schlumberger's activities. To achieve that we recruit the most talented scientists from a variety of scientific and engineering backgrounds, and give them opportunities to advance their fields of expertise as well as to develop solutions of significant industrial impact. The Schlumberger Gould Research Centre strongly encourages the self-development of its scientists, offers high-end experimental facilities and scientific resources, and maintains strong collaborations with academic and industrial research groups worldwide. Schlumberger is currently developing new drilling systems with a high degree of autonomy and intelligence which will change the way the industry drills wells.

The ubiquitous presence of sequence data across fields such as the web, healthcare, bioinformatics, and text mining has made sequence mining a vital research area. However, sequence mining is particularly challenging because of difficulty in finding (dis)similarity/distance between sequences. This is because a distance measure between sequences is not obvious due to their unstructuredness---arbitrary strings of arbitrary length. Feature representations, such as n-grams, are often used but they either compromise on extracting both short- and long-term sequence patterns or have a high computation. We propose a new function, Sequence Graph Transform (SGT), that extracts the short- and long-term sequence features and embeds them in a finite-dimensional feature space. Importantly, SGT has low computation and can extract any amount of short- to long-term patterns without any increase in the computation, also proved theoretically in this paper. Due to this, SGT yields superior result with significantly higher accuracy and lower computation compared to the existing methods. We show it via several experimentation and SGT's real world application for clustering, classification, search and visualization as examples.

Artificial intelligence (AI), machine learning (ML), and robots are the sights and sounds of science fiction books and movies. Isaac Asimov's Three Laws of Robotics, first introduced in the 1942 short story "Runaround," became the backbone for his novel I, Robot and its film adaptation (Figure 1). Although we are still far away from achieving what movie producers and sci-fi writers have envisioned, the state of AI and ML has progressed significantly. AI software has also been in use for decades but advances in ML, including the use of deep neural networks (DNNs), are making headlines in application areas like self-driving cars. The movie I, Robot has robots that should be following Asimov's Three Laws of Robotics.

Estimation, recognition, and near-future prediction of 3D trajectories based on their two dimensional projections available from one camera source is an exceptionally difficult problem due to uncertainty in the trajectories and environment, high dimensionality of the specific trajectory states, lack of enough labeled data and so on. In this article, we propose a solution to solve this problem based on a novel deep learning model dubbed Disjunctive Factored Four-Way Conditional Restricted Boltzmann Machine (DFFW-CRBM). Our method improves state-of-the-art deep learning techniques for high dimensional time-series modeling by introducing a novel tensor factorization capable of driving forth order Boltzmann machines to considerably lower energy levels, at no computational costs. DFFW-CRBMs are capable of accurately estimating, recognizing, and performing near-future prediction of three-dimensional trajectories from their 2D projections while requiring limited amount of labeled data. We evaluate our method on both simulated and real-world data, showing its effectiveness in predicting and classifying complex ball trajectories and human activities.

Knowledge of biological processes captured in such equations, when solutions to them match measurements made from the system of interest, help confirm our understanding of systems level function. Examples of such models include cell cycle progression (Chen et al., 2000), integrate and fire generation of heart pacemaker pulses (Zhang et al., 2000) and cellular behavior in synchrony with the circadian cycle (Leloup and Goldbeter, 2003). A particular appeal of modeling is that models can be interrogated with what if type questions to improve our understanding of the system, or be used to make quantitative predictions in domains in which measurements are unavailable. A central issue in developing computational models of biological systems is setting parameters such as rate constants of biochemical reactions, synthesis and decay rates of macromolecules, delays incurred in transcription of genes and translation of proteins, and sharpness of nonlinear effects (Hill coefficient) are examples of such parameters. Parameter values are usually determined by conducting in vitro experiments (e.g.