The connection between machine learning and statistical physics has long been appreciated [1-9], but deeper relationships continue to be uncovered. For example, techniques used to pre-train neural networks [8] have more recently been interpreted in terms of the renor-malization group [10]. In the other direction there has been a sharp increase in applications of machine learning to chemistry, material science, and condensed matter physics [11-19], which are sources of highly-structured data and could be a good testing ground for machine learning techniques. A recent trend in both physics and machine learning is an appreciation for the power of tensor methods. In machine learning, tensor decompositions can be used to solve non-convex optimization tasks [20, 21] and make progress on many other important problems [22-24], while in physics, great strides have been made in manipulating large vectors arising in quantum mechanics by decomposing them as tensor networks [25-27]. The most successful types of tensor networks avoid the curse of dimensionality by incorporating only low-order tensors, yet accurately reproduce very high-order tensors through a particular geometry of tensor contractions [27]. Another context where very large vectors arise is in nonlinear kernel learning, where input vectors x are mapped into a higher dimensional space via a feature map Φ( x) before being classified by a decision function f ( x) W · Φ( x).

Linking human whole-body motion and natural language is of great interest for the generation of semantic representations of observed human behaviors as well as for the generation of robot behaviors based on natural language input. While there has been a large body of research in this area, most approaches that exist today require a symbolic representation of motions (e.g. in the form of motion primitives), which have to be defined a-priori or require complex segmentation algorithms. In contrast, recent advances in the field of neural networks and especially deep learning have demonstrated that sub-symbolic representations that can be learned end-to-end usually outperform more traditional approaches, for applications such as machine translation. In this paper we propose a generative model that learns a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks (RNNs) and sequence-to-sequence learning. Our approach does not require any segmentation or manual feature engineering and learns a distributed representation, which is shared for all motions and descriptions. We evaluate our approach on 2,846 human whole-body motions and 6,187 natural language descriptions thereof from the KIT Motion-Language Dataset. Our results clearly demonstrate the effectiveness of the proposed model: We show that our model generates a wide variety of realistic motions only from descriptions thereof in form of a single sentence. Conversely, our model is also capable of generating correct and detailed natural language descriptions from human motions.

We study the relationship between performance and practice by analyzing the activity of many players of a casual online game. We find significant heterogeneity in the improvement of player performance, given by score, and address this by dividing players into similar skill levels and segmenting each player's activity into sessions, that is, sequence of game rounds without an extended break. After disaggregating data, we find that performance improves with practice across all skill levels. More interestingly, players are more likely to end their session after an especially large improvement, leading to a peak score in their very last game of a session. In addition, success is strongly correlated with a lower quitting rate when the score drops, and only weakly correlated with skill, in line with psychological findings about the value of persistence and “grit:” successful players are those who persist in their practice despite lower scores. Finally, we train an ε-machine, a type of hidden Markov model, and find a plausible mechanism of game play that can predict player performance and quitting the game. Our work raises the possibility of real-time assessment and behavior prediction that can be used to optimize human performance.

This is the first article in a series about most used Java libraries, frameworks and API's in big data projects. Java, one of the most broadly used programming languages in big data projects, owes part of its popularity to its extensive ecosystem. Programming in Java provides the access to this ecosystem that consists of several libraries, frameworks, and APIs. Within a series of articles I am going to briefly describe the most used Java libraries, frameworks, and APIs for big data projects. There are numerous third-party libraries for Java programming language.

Markov Chain Monte Carlo methods have revolutionised mathematical computation and enabled statistical inference within many previously intractable models. In this context, Hamiltonian dynamics have been proposed as an efficient way of building chains which can explore probability densities efficiently. The method emerges from physics and geometry and these links have been extensively studied by a series of authors through the last thirty years. However, there is currently a gap between the intuitions and knowledge of users of the methodology and our deep understanding of these theoretical foundations. The aim of this review is to provide a comprehensive introduction to the geometric tools used in Hamiltonian Monte Carlo at a level accessible to statisticians, machine learners and other users of the methodology with only a basic understanding of Monte Carlo methods. This will be complemented with some discussion of the most recent advances in the field which we believe will become increasingly relevant to applied scientists.

In this paper, we consider a finite-horizon Markov decision process (MDP) for which the objective at each stage is to minimize a quantile-based risk measure (QBRM) of the sequence of future costs; we call the overall objective a dynamic quantile-based risk measure (DQBRM). In particular, we consider optimizing dynamic risk measures where the one-step risk measures are QBRMs, a class of risk measures that includes the popular value at risk (VaR) and the conditional value at risk (CVaR). Although there is considerable theoretical development of risk-averse MDPs in the literature, the computational challenges have not been explored as thoroughly. We propose data-driven and simulation-based approximate dynamic programming (ADP) algorithms to solve the risk-averse sequential decision problem. We address the issue of inefficient sampling for risk applications in simulated settings and present a procedure, based on importance sampling, to direct samples toward the "risky region" as the ADP algorithm progresses. Finally, we show numerical results of our algorithms in the context of an application involving risk-averse bidding for energy storage.

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.

Online reviews provided by consumers are a valuable asset for e-Commerce platforms, influencing potential consumers in making purchasing decisions. However, these reviews are of varying quality, with the useful ones buried deep within a heap of non-informative reviews. In this work, we attempt to automatically identify review quality in terms of its helpfulness to the end consumers. In contrast to previous works in this domain exploiting a variety of syntactic and community-level features, we delve deep into the semantics of reviews as to what makes them useful, providing interpretable explanation for the same. We identify a set of consistency and semantic factors, all from the text, ratings, and timestamps of user-generated reviews, making our approach generalizable across all communities and domains. We explore review semantics in terms of several latent factors like the expertise of its author, his judgment about the fine-grained facets of the underlying product, and his writing style. These are cast into a Hidden Markov Model -- Latent Dirichlet Allocation (HMM-LDA) based model to jointly infer: (i) reviewer expertise, (ii) item facets, and (iii) review helpfulness. Large-scale experiments on five real-world datasets from Amazon show significant improvement over state-of-the-art baselines in predicting and ranking useful reviews.

Current recommender systems exploit user and item similarities by collaborative filtering. Some advanced methods also consider the temporal evolution of item ratings as a global background process. However, all prior methods disregard the individual evolution of a user's experience level and how this is expressed in the user's writing in a review community. In this paper, we model the joint evolution of user experience, interest in specific item facets, writing style, and rating behavior. This way we can generate individual recommendations that take into account the user's maturity level (e.g., recommending art movies rather than blockbusters for a cinematography expert). As only item ratings and review texts are observables, we capture the user's experience and interests in a latent model learned from her reviews, vocabulary and writing style. We develop a generative HMM-LDA model to trace user evolution, where the Hidden Markov Model (HMM) traces her latent experience progressing over time -- with solely user reviews and ratings as observables over time. The facets of a user's interest are drawn from a Latent Dirichlet Allocation (LDA) model derived from her reviews, as a function of her (again latent) experience level. In experiments with five real-world datasets, we show that our model improves the rating prediction over state-of-the-art baselines, by a substantial margin. We also show, in a use-case study, that our model performs well in the assessment of user experience levels.

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the future observations in the process. We devise a learning algorithm running through epochs, in each epoch we employ spectral techniques to learn the POMDP parameters from a trajectory generated by a fixed policy. At the end of the epoch, an optimization oracle returns the optimal memoryless planning policy which maximizes the expected reward based on the estimated POMDP model. We prove an order-optimal regret bound with respect to the optimal memoryless policy and efficient scaling with respect to the dimensionality of observation and action spaces.