W e present a Markov model at the discourse level for Steven Pinker's "mentalese", or chains of mental states that transcend the spoken/written forms. Such (potentially) universal temporal structures of textual pa tterns lead us to a language-independent semantic representation, or a translationally-invariant word embe dding, thereby forming the common ground for both comprehensibility within a given language and transla tability between different languages. Applying our model to documents of moderate lengths, without relying on external knowledge bases, we reconcile Noam Chomsky's "poverty of stimulus" paradox with statisti cal learning of natural languages. W e human beings distinguish ourselves from other animals ( 1-3), in that our brain development ( 4-6) enables us to convey sophisticated ideas and to share individual experience s, via languages ( 7-9). Texts written in natural languages constitute a major medium that perpetuates our civilizations ( 10), as a cumulative body of knowledge.

In an image recognition application, the raw input may be a matrix of pixels; the first representational layer may abstract the pixels and encode edges; the second layer may compose and encode arrangements of edges; the third layer may encode a nose and eyes; and the fourth layer may recognize that the image contains a face. Importantly, a deep learning process can learn which features to optimally place in which level on its own.

The focus of this paper is a Bayesian framework for solving a class of problems termed multi-agent inverse reinforcement learning (MIRL). Compared to the well-known inverse reinforcement learning (IRL) problem, MIRL is formalized in the context of stochastic games, which generalize Markov decision processes to game theoretic scenarios. We establish a theoretical foundation for competitive two-agent zero-sum MIRL problems and propose a Bayesian solution approach in which the generative model is based on an assumption that the two agents follow a minimax bi-policy. Numerical results are presented comparing the Bayesian MIRL method with two existing methods in the context of an abstract soccer game. Investigation centers on relationships between the extent of prior information and the quality of learned rewards. Results suggest that covariance structure is more important than mean value in reward priors.

Speech is the way of communication between people. The speech recognition is a software invention which converts our spoken language into a machine-readable format. Nowadays speech recognition is useful for interaction between human and machines or mobile devices. So, it is very important. Speech recognition is mainly divided into two parts.

Thanh-Toan Do University of Liverpool thanh-toan.do@liverpool.ac.uk Abstract W e introduce a new, rigorously-formulated Bayesian meta-learning algorithm that learns a probability distribution of model parameter prior for few-shot learning. The proposed algorithm employs a gradient-based variational inference to infer the posterior of model parameters to a new task. Our algorithm can be applied to any model architecture and can be implemented in various machine learning paradigms, including regression and classification. W e show that the models trained with our proposed meta-learning algorithm are well calibrated and accurate, with state-of-the-art calibration and classification results on two few-shot classification benchmarks (Omniglot and Mini-ImageNet), and competitive results in a multi-modal task-distribution regression. 1. Introduction Machine learning, in particular deep learning, has thrived during the last decade, producing results that were previously considered to be infeasible in several areas. For instance, outstanding results have been achieved in speech and image understanding [1-4], and medical image analysis [5]. However, the development of these machine learning methods typically requires a large number of training samples to achieve notable performance. Such requirement contrasts with the human ability of quickly adapting to new learning tasks using few "training" samples. This difference may be due to the fact that humans tend to exploit prior knowledge to facilitate the learning of new tasks, while machine learning algorithms often do not use any prior knowledge (e.g., training from scratch with random initialisation) [6] or rely on weak prior knowledge to learn new tasks (e.g., training from pre-trained models) [7]. This challenge has motivated the design of machine learning methods that can make more effective use of prior knowledge to adapt to new learning tasks using few training samples [8].

Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks, alternative non-likelihood training criteria have been proposed. Whilst not necessarily statistically efficient, these alternatives may better match user requirements such as sharp image generation. A general variational method for training probabilistic latent variable models using maximum likelihood is well established; however, how to train latent variable models using other f-divergences is comparatively unknown. We discuss a variational approach that, when combined with the recently introduced Spread Divergence, can be applied to train a large class of latent variable models using any f-divergence.

--Smooth handling of pedestrian interactions is a key requirement for Autonomous V ehicles (A V) and Advanced Driver Assistance Systems (ADAS). Such systems call for early and accurate prediction of a pedestrian's crossing/not-crossing behaviour in front of the vehicle. We stress on the necessity of early prediction for smooth operation of such systems. We introduce the influence of vehicle interactions on pedestrian intention for this purpose. In this paper, we show a discernible advance in prediction time aided by the inclusion of such vehicle interaction context. We apply our methods to two different datasets, one in-house collected - NTU dataset and another public real-life benchmark - JAAD dataset. We also propose a generic graphical model Factored Latent-Dynamic Conditional Random Fields (FLDCRF) for single and multi-label sequence prediction as well as joint interaction modeling tasks. While the existing best system predicts pedestrian stopping behaviour with 70% accuracy 0.38 seconds before the actual events, our system achieves such accuracy at least 0.9 seconds on an average before the actual events across datasets. Personal use of this material is permitted. S we enter the era of autonomous driving with the first ever self-driving taxi launched in December 2018, smooth handling of pedestrian interactions still remains a challenge. The tradeoff is between on-road pedestrian safety and smoothness of the ride. Recent user experiences and available online footage suggest conservative autonomous rides resulting from the emphasis on on-road pedestrian safety . T o achieve rapid user adoption, the A Vs must be able to simulate a smooth human driver-like experience without unnecessary interruptions, in addition to ensuring 100% pedestrian safety . Automated braking systems in an ADAS tackle the emergency pedestrian interactions. These brakes get activated on detecting pedestrians' crossing behaviours within the vehicle safety range. A future ADAS must be able of offer a smoother experience on such interactions. The key to a safe and smooth autonomous pedestrian interaction lies in early and accurate prediction of a pedestrian's crossing/not-crossing behaviour in front of the vehicle. Accurate and timely prediction of pedestrian behaviour ensures on-road pedestrian safety, while early anticipation of the crossing/not-crossing behaviour offers more path planning time and consequently a smoother control over the vehicle dynamics. Recent works on on-road pedestrian behaviour prediction ([1] - [15]) rely on a pedestrian's motion, skeletal pose, his/her location in scene (on road, at curb etc.) and certain static context variables (e.g., presence of zebra crossings, traffic lights etc.).

Neural dialogue models, despite their successes, still suffer from lack of relevance, diversity, and in many cases coherence in their generated responses. These issues have been attributed to reasons including (1) short-range model architectures that capture limited temporal dependencies, (2) limitations of the maximum likelihood training objective, (3) the concave entropy profile of dialogue datasets resulting into short and generic responses, and (4) out-of-vocabulary problem leading to generation of a large number of $<$UNK$>$ tokens. Autoregressive transformer models such as GPT-2, although trained with the maximum likelihood objective, do not suffer from the out-of-vocabulary problem and have demonstrated an excellent ability to capture long-range structures in language modeling tasks. In this paper, we examine the use of autoregressive transformer models for multi-turn dialogue response generation. In our experiments, we employ small and medium GPT-2 models (with publicly available pretrained language model parameters) on the open-domain Movie Triples dataset and the closed-domain Ubuntu Dialogue dataset. The models (with and without pretraining) achieve significant improvements over the baselines for multi-turn dialogue response generation. They also produce state-of-the-art performance on the two datasets based on several metrics, including BLEU, ROGUE, and distinct n-gram.

Seasonal influenza infects between 10 and 50 million people in the United States every year, overburdening hospitals during weeks of peak incidence. Named by the CDC as an important tool to fight the damaging effects of these epidemics, accurate forecasts of influenza and influenza-like illness (ILI) forewarn public health officials about when, and where, seasonal influenza outbreaks will hit hardest. Multi-model ensemble forecasts---weighted combinations of component models---have shown positive results in forecasting. Ensemble forecasts of influenza outbreaks have been static, training on all past ILI data at the beginning of a season, generating a set of optimal weights for each model in the ensemble, and keeping the weights constant. We propose an adaptive ensemble forecast that (i) changes model weights week-by-week throughout the influenza season, (ii) only needs the current influenza season's data to make predictions, and (iii) by introducing a prior distribution, shrinks weights toward the reference equal weighting approach and adjusts for observed ILI percentages that are subject to future revisions. We investigate the prior's ability to impact adaptive ensemble performance and, after finding an optimal prior via a cross-validation approach, compare our adaptive ensemble's performance to equal-weighted and static ensembles. Applied to forecasts of short-term ILI incidence at the regional and national level in the US, our adaptive model outperforms a naive equal-weighted ensemble, and has similar or better performance to the static ensemble, which requires multiple years of training data. Adaptive ensembles are able to quickly train and forecast during epidemics, and provide a practical tool to public health officials looking for forecasts that can conform to unique features of a specific season.

The goal is to capture the sensitivity of inferential proc edures to the presence of outliers in the data and misspecifications in the modelling a ssumptions, and to mitigate overly large sensitivity. The Bayesian approach has been fo cused on capturing possible anomalies in the observed data via the model and in choosing p riors that have minimal effect on inferences. The frequentist approach, on the other hand, has focused on the development of estimators that identify and guard against o utliers in the data. We refer the reader to [ Hub11, Chap 15] for a comprehensive discussion.