Memory-augmented neural networks (MANNs) have been shown to outperform other recurrent neural network architectures on a series of artificial sequence learning tasks, yet they have had limited application to real-world tasks. We evaluate direct application of Neural Turing Machines (NTM) and Differentiable Neural Computers (DNC) to machine translation. We further propose and evaluate two models which extend the attentional encoder-decoder with capabilities inspired by memory augmented neural networks. We evaluate our proposed models on IWSLT Vietnamese to English and ACL Romanian to English datasets. Our proposed models and the memory augmented neural networks perform similarly to the attentional encoder-decoder on the Vietnamese to English translation task while have a 0.3-1.9 lower BLEU score for the Romanian to English task. Interestingly, our analysis shows that despite being equipped with additional flexibility and being randomly initialized memory augmented neural networks learn an algorithm for machine translation almost identical to the attentional encoder-decoder.

With the advent of deep learning, the performance of text classification models have been improved significantly. Nevertheless, the successful training of a good classification model requires a sufficient amount of labeled data, while it is always expensive and time consuming to annotate data. With the rapid growth of digital data, similar classification tasks can typically occur in multiple domains, while the availability of labeled data can largely vary across domains. Some domains may have abundant labeled data, while in some other domains there may only exist a limited amount (or none) of labeled data. Meanwhile text classification tasks are highly domain-dependent -- a text classifier trained in one domain may not perform well in another domain. In order to address these issues, in this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously under a discrepancy based co-learning framework, aiming to improve the classifiers' generalization capacity with the learned features. We conduct experiments on multi-domain sentiment classification datasets. The results show the proposed approach achieves the state-of-the-art MDTC performance.

A large body of animation research focuses on optimization of movement control, either as action sequences or policy parameters. However, as closed-form expressions of the objective functions are often not available, our understanding of the optimization problems is limited. Building on recent work on analyzing neural network training, we contribute novel visualizations of high-dimensional control optimization landscapes; this yields insights into why control optimization is hard and why common practices like early termination and spline-based action parameterizations make optimization easier. For example, our experiments show how trajectory optimization can become increasingly ill-conditioned with longer trajectories, but parameterizing control as partial target states - e.g., target angles converted to torques using a PD-controller - can act as an efficient preconditioner. Both our visualizations and quantitative empirical data also indicate that neural network policy optimization scales better than trajectory optimization for long planning horizons. Our work advances the understanding of movement optimization and our visualizations should also provide value in educational use.

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the representation power of VAEs is limited due to two reasons: (1) the Gaussian assumption is often made on the variational posteriors; and meanwhile (2) a notorious "posterior collapse" issue occurs. In this paper, we advocate sample-based representations of variational distributions for natural language, leading to implicit latent features, which can provide flexible representation power compared with Gaussian-based posteriors. We further develop an LVM to directly match the aggregated posterior to the prior. It can be viewed as a natural extension of VAEs with a regularization of maximizing mutual information, mitigating the "posterior collapse" issue. We demonstrate the effectiveness and versatility of our models in various text generation scenarios, including language modeling, unaligned style transfer, and dialog response generation. The source code to reproduce our experimental results is available on GitHub.

The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems. It is nonlinear and nonconvex and computes the generator setpoints for power and voltage, given a set of load demands. It is often needed to be solved repeatedly under various conditions, either in real-time or in large-scale studies. This need is further exacerbated by the increasing stochasticity of power systems due to renewable energy sources in front and behind the meter. To address these challenges, this paper presents a deep learning approach to the OPF. The learning model exploits the information available in the prior states of the system (which is commonly available in practical applications), as well as a dual Lagrangian method to satisfy the physical and engineering constraints present in the OPF. The proposed model is evaluated on a large collection of realistic power systems. The experimental results show that its predictions are highly accurate with average errors as low as 0.2%. Additionally, the proposed approach is shown to improve the accuracy of widely adopted OPF linear DC approximation by at least two orders of magnitude.

Personal assistant AI systems such as Siri, Cortana, and Alexa have become widely used as a means to accomplish tasks through natural language commands. However, components in these systems generally rely on supervised machine learning algorithms that require large amounts of hand-annotated training data, which is expensive and time consuming to collect. The ability to incorporate unsupervised, weakly supervised, or distantly supervised data holds significant promise in overcoming this bottleneck. In this paper, we describe a framework that leverages user engagement signals (user behaviors that demonstrate a positive or negative response to content) to automatically create granular entity labels for training data augmentation. Strategies such as multi-task learning and validation using an external knowledge base are employed to incorporate the engagement annotated data and to boost the model's accuracy on a sequence labeling task. Our results show that learning from data automatically labeled by user engagement signals achieves significant accuracy gains in a production deep learning system, when measured on both the sequence labeling task as well as on user facing results produced by the system end-to-end. We believe this is the first use of user engagement signals to help generate training data for a sequence labeling task on a large scale, and can be applied in practical settings to speed up new feature deployment when little human annotated data is available.

--Advances in the field of Machine Learning and Deep Neural Networks (DNNs) has enabled rapid development of sophisticated and autonomous systems. However, the inherent complexity to rigorously assure the safe operation of such systems hinders their real-world adoption in safety-critical domains such as aerospace and medical devices. Hence, there is a surge in interest to explore the use of advanced mathematical techniques such as formal methods to address this challenge. In fact, the initial results of such efforts are promising. Along these lines, we propose the use of quantifier elimination (QE) -- a formal method technique, as a complimentary technique to the state-of-the-art static analysis and verification procedures. Using an airborne collision avoidance DNN as a case example, we illustrate the use of QE to formulate the precise range forward propagation through a network as well as analyze its robustness. We discuss the initial results of this ongoing work and explore the future possibilities of extending this approach and/or integrating it with other approaches to perform advanced safety assurance of DNNs. Recently, there is a tremendous surge of interest within the aerospace community to leverage advances in Machine Learning (ML) to develop sophisticated software for large, autonomous avionic systems such as unmanned aircrafts. In fact, the inherent ability of the modern structurally complex computing systems such as Deep Neural Networks (DNN), that automatically learn and generalize behaviors based on a set of training data rather than explicit programming based on requirements, makes it a natural choice for developing autonomous components for aircraft. However, there is a widespread apprehension about deploying such systems in the real-world since it has not been possible to rigorously interpret and assure the safe functional boundaries and behaviors of the DNNs due to their structural complexity and behavioural immensity [1, 2, 3]. For instance, analyzing the robustness of DNNs against adversarial attacks [4, 5, 6] -- small perturbations to inputs that lead to unsafe outputs, remains as an open safety assurance concern.

Comprehensive IT support teams in large scale organizations require more man power for handling engagement and requests of employees from different channels on a 24*7 basis. Automated email technical queries help desk is proposed to have instant real-time quick solutions and email categorisation. Email topic modelling with various machine learning, deep-learning approaches are compared with different features for a scalable, generalised solution along with sure-shot static rules. Email's title, body, attachment, OCR text, and some feature engineered custom features are given as input elements. XGBoost cascaded hierarchical models, Bi-LSTM model with word embeddings perform well showing 77.3 overall accuracy For the real world corporate email data set. By introducing the thresholding techniques, the overall automation system architecture provides 85.6 percentage of accuracy for real world corporate emails. Combination of quick fixes, static rules, ML categorization as a low cost inference solution reduces 81 percentage of the human effort in the process of automation and real time implementation.

In autonomous navigation, a planning system reasons about other agents to plan a safe and plausible trajectory. Before planning starts, agents are typically processed with computationally intensive models for recognition, tracking, motion estimation and prediction. With limited computational resources and a large number of agents to process in real time, it becomes important to efficiently rank agents according to their impact on the decision making process. This allows spending more time processing the most important agents. We propose a system to rank agents around an autonomous vehicle (AV) in real time. We automatically generate a ranking data set by running the planner in simulation on real-world logged data, where we can afford to run more accurate and expensive models on all the agents. The causes of various planner actions are logged and used for assigning ground truth importance scores. The generated data set can be used to learn ranking models. In particular, we show the utility of combining learned features, via a convolutional neural network, with engineered features designed to capture domain knowledge. We show the benefits of various design choices experimentally. When tested on real AVs, our system demonstrates the capability of understanding complex driving situations.

Embodied avatars as virtual agents have many applications and provide benefits over disembodied agents, allowing non-verbal social and interactional cues to be leveraged, in a similar manner to how humans interact with each other. We present an open embodied avatar built upon the Unreal Engine that can be controlled via a simple python programming interface. The avatar has lip syncing (phoneme control), head gesture and facial expression (using either facial action units or cardinal emotion categories) capabilities. We release code and models to illustrate how the avatar can be controlled like a puppet or used to create a simple conversational agent using public application programming interfaces (APIs). GITHUB link: https://github.com/danmcduff/AvatarSim