In this work, we adopt the teacherstudent (T/S)learning technique using a parallel clean and noisy corpus for improving automatic speech recognition (ASR) performance under multimedia noise. On top of that, we apply a logits selection method which only preserves the k highest values to prevent wrong emphasis of knowledge from the teacher and to reduce bandwidth needed for transferring data. We incorporate up to 8000 hours of untranscribed data for training and present our results on sequence trained models apartfrom cross entropy trained ones. The best sequence trained student model yields relative word error rate (WER) reductions of approximately 10.1%, 28.7% and 19.6% on our clean, simulated noisy and real test sets respectively comparing toa sequence trained teacher. Index Terms-- automatic speech recognition, noise robustness, teacher-studenttraining, domain adaptation 1. INTRODUCTION With the exponential growth of big data and computing power, automatic speech recognition (ASR) technology has been successfully used in many applications. People can do voice search using mobile devices.

We propose a deep generative Markov State Model (DeepGenMSM) learning framework for inference of metastable dynamical systems and prediction of trajectories. After unsupervised training on time series data, the model contains (i) a probabilistic encoder that maps from high-dimensional configuration space to a small-sized vector indicating the membership to metastable (long-lived) states, (ii) a Markov chain that governs the transitions between metastable states and facilitates analysis of the long-time dynamics, and (iii) a generative part that samples the conditional distribution of configurations in the next time step. The model can be operated in a recursive fashion to generate trajectories to predict the system evolution from a defined starting state and propose new configurations. The DeepGenMSM is demonstrated to provide accurate estimates of the long-time kinetics and generate valid distributions for molecular dynamics (MD) benchmark systems. Remarkably, we show that DeepGenMSMs are able to make long time-steps in molecular configuration space and generate physically realistic structures in regions that were not seen in training data.

We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and E-$\text{RL}^2$. Results are presented on a novel environment we call `Krazy World' and a set of maze environments. We show E-MAML and E-$\text{RL}^2$ deliver better performance on tasks where exploration is important.

The Vision-and-Language Navigation (VLN) task entails an agent following navigational instruction in photo-realistic unknown environments. This challenging task demands that the agent be aware of which instruction was completed, which instruction is needed next, which way to go, and its navigation progress towards the goal. In this paper, we introduce a self-monitoring agent with two complementary components: (1) visual-textual co-grounding module to locate the instruction completed in the past, the instruction required for the next action, and the next moving direction from surrounding images and (2) progress monitor to ensure the grounded instruction correctly reflects the navigation progress. We test our selfmonitoring agent on a standard benchmark and analyze our proposed approach through a series of ablation studies that elucidate the contributions of the primary components. Using our proposed method, we set the new state of the art by a significant margin (8% absolute increase in success rate on the unseen test set). Recently, the Vision-and-Language (VLN) navigation task (Anderson et al., 2018b), which requires the agent to follow natural language instructions to navigate through a photo-realistic unknown environment, has received significant attention (Wang et al., 2018b; Fried et al., 2018). In the VLN task, an agent is placed in an unknown realistic environment and is required to follow natural language instructions to navigate from its starting location to a target location. Instead, the agent needs to be aware of its navigation status through the association between the sequence of observed visual inputs to instructions. Consider an example as shown in Figure 1, given the instruction "Exit the bedroom and go towards the table. Go to the stairs on the left of the couch. Wait on the third step.", the agent first needs to locate which instruction is needed for the next movement, which in turn requires the agent to be aware of (i.e., to explicitly represent or have an attentional focus on) which instructions were completed or ongoing in the previous steps.

Student performance modelling (SPM) is a critical step to assessing and improving students performances in their learning discourse. However, most existing SPM are based on statistical approaches, which on one hand are based on probability, depicting that results are based on estimation; and on the other hand, actual influences of hidden factors that are peculiar to students, lecturers, learning environment and the family, together with their overall effect on student performance have not been exhaustively investigated. In this paper, Student Performance Models (SPM) for improving students performance in programming courses were developed using M5P Decision Tree (MDT) and Linear Regression Classifier (LRC). The data used was gathered using a structured questionnaire from 295 students in 200 and 300 levels of study who offered Web programming, C or JAVA at Federal University, Oye-Ekiti, Nigeria between 2012 and 2016. Hidden factors that are significant to students performance in programming were identified. The relevant data gathered, normalized, coded and prepared as variable and factor datasets, and fed into the MDT algorithm and LRC to develop the predictive models. The evaluation results obtained indicate that the variable-based LRC produced the best model in terms of MAE, RMSE, RAE and the RRSE having yielded the least values in all the evaluations conducted. Further results obtained established the strong significance of attitude of students and lecturers, fearful perception of students, erratic power supply, university facilities, student health and students attendance to the performance of students in programming courses. The variable-based LRC model presented in this paper could provide baseline information about students performance thereby offering better decision making towards improving teaching/learning outcomes in programming courses.

Automatic human affect recognition is a key step towards more natural human-computer interaction. Recent trends include recognition in the wild using a fusion of audiovisual and physiological sensors, a challenging setting for conventional machine learning algorithms. Since 2010, novel deep learning algorithms have been applied increasingly in this field. In this paper, we review the literature on human affect recognition between 2010 and 2017, with a special focus on approaches using deep neural networks. By classifying a total of 950 studies according to their usage of shallow or deep architectures, we are able to show a trend towards deep learning. Reviewing a subset of 233 studies that employ deep neural networks, we comprehensively quantify their applications in this field. We find that deep learning is used for learning of (i) spatial feature representations, (ii) temporal feature representations, and (iii) joint feature representations for multimodal sensor data. Exemplary state-of-the-art architectures illustrate the progress. Our findings show the role deep architectures will play in human affect recognition, and can serve as a reference point for researchers working on related applications.

This paper presents a semantic brain computer interface (BCI) agent with particle swarm optimization (PSO) based on a Fuzzy Markup Language (FML) for Go learning and prediction applications. Additionally, we also establish an Open Go Darkforest (OGD) cloud platform with Facebook AI research (FAIR) open source Darkforest and ELF OpenGo AI bots. The Japanese robot Palro will simultaneously predict the move advantage in the board game Go to the Go players for reference or learning. The proposed semantic BCI agent operates efficiently by the human-based BCI data from their brain waves and machine-based game data from the prediction of the OGD cloud platform for optimizing the parameters between humans and machines. Experimental results show that the proposed human and smart machine co-learning mechanism performs favorably. We hope to provide students with a better online learning environment, combining different kinds of handheld devices, robots, or computer equipment, to achieve a desired and intellectual learning goal in the future.

Artificial intelligence can quickly and accurately rate the amount of atrophy in parts of the brain, which can help in the diagnosis and research of dementia. A new study reported in arXiv.org, It is an inexpensive way to quantify brain atrophy and helps improve the specificity and sensitivity of diagnosis. These visual atrophy ratings aren't used widely because the ratings are inherently subjective, researchers note. Radiologists performing them need to be experienced in such work, and the assessments are tedious and time consuming--it takes several minutes per image for a neuroradiologist to perform the rating. And while the rating is potentially useful in a clinical setting, the current process does not easily enable the study of larger groups of images, which is important for research purposes.

GREENLIGHT, Business coaching firm, launches a new Artificial Intelligence (AI) simulator product to train startup founders how to overcome obstacles to be sustainable and profitable. The product was code-named "Crucible". A team of Artificial Intelligence (AI) tech developers, gaming experts, and serial entrepreneurs brought their domain expertise into a continuous learning platform and designed crucible product. A proprietary Smart Start framework from Greenlight is ued for assessing and scoring managerial competency and further improving capability with targeted action plans and simulating successful outcomes. Crucible was tested with startups from Columbia University and several candidates competing in the IBM Watson AI XPRIZE.

Using distinct steps makes it possible to rerun only the steps you need, as you tweak and test your workflow. A step is a computational unit in the pipeline. As shown in the preceding diagram, the task of preparing data can involve many steps. These include, but aren't limited to, normalization, transformation, validation, and featurization. Data sources and intermediate data are reused across the pipeline, which saves compute time and resources.