With the widespread use of intelligent systems, such as smart speakers, addressee recognition has become a concern in human-computer interaction, as more and more people expect such systems to understand complicated social scenes, including those outdoors, in cafeterias, and hospitals. Because previous studies typically focused only on pre-specified tasks with limited conversational situations such as controlling smart homes, we created a mock dataset called Addressee Recognition in Visual Scenes with Utterances (ARVSU) that contains a vast body of image variations in visual scenes with an annotated utterance and a corresponding addressee for each scenario. We also propose a multi-modal deep-learning-based model that takes different human cues, specifically eye gazes and transcripts of an utterance corpus, into account to predict the conversational addressee from a specific speaker's view in various real-life conversational scenarios. To the best of our knowledge, we are the first to introduce an end-to-end deep learning model that combines vision and transcripts of utterance for addressee recognition. As a result, our study suggests that future addressee recognition can reach the ability to understand human intention in many social situations previously unexplored, and our modality dataset is a first step in promoting research in this field.

In this paper, we present a robotic navigation algorithm with natural language interfaces, which enables a robot to safely walk through a changing environment with moving persons by following human instructions such as "go to the restaurant and keep away from people". We first classify human instructions into three types: the goal, the constraints, and uninformative phrases. Next, we provide grounding for the extracted goal and constraint items in a dynamic manner along with the navigation process, to deal with the target objects that are too far away for sensor observation and the appearance of moving obstacles like humans. In particular, for a goal phrase (e.g., "go to the restaurant"), we ground it to a location in a predefined semantic map and treat it as a goal for a global motion planner, which plans a collision-free path in the workspace for the robot to follow. For a constraint phrase (e.g., "keep away from people"), we dynamically add the corresponding constraint into a local planner by adjusting the values of a local costmap according to the results returned by the object detection module. The updated costmap is then used to compute a local collision avoidance control for the safe navigation of the robot. By combining natural language processing, motion planning, and computer vision, our developed system is demonstrated to be able to successfully follow natural language navigation instructions to achieve navigation tasks in both simulated and real-world scenarios. Videos are available at https://sites.google.com/view/snhi

We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to leverage the semantics of SQL. It detects and excludes faulty programs during the decoding procedure by conditioning on the execution of partially generated program. The mechanism can be used with any autoregressive generative model, which we demonstrate on four state-of-the-art recurrent or template-based semantic parsing models. We demonstrate that execution guidance universally improves model performance on various text-to-SQL datasets with different scales and query complexity: WikiSQL, ATIS, and GeoQuery. As a result, we achieve new state-of-the-art execution accuracy of 83.8% on WikiSQL.

The reinforcement learning community has made great strides in designing algorithms capable of exceeding human performance on specific tasks. These algorithms are mostly trained one task at the time, each new task requiring to train a brand new agent instance. This means the learning algorithm is general, but each solution is not; each agent can only solve the one task it was trained on. In this work, we study the problem of learning to master not one but multiple sequential-decision tasks at once. A general issue in multi-task learning is that a balance must be found between the needs of multiple tasks competing for the limited resources of a single learning system. Many learning algorithms can get distracted by certain tasks in the set of tasks to solve. Such tasks appear more salient to the learning process, for instance because of the density or magnitude of the in-task rewards. This causes the algorithm to focus on those salient tasks at the expense of generality. We propose to automatically adapt the contribution of each task to the agent's updates, so that all tasks have a similar impact on the learning dynamics. This resulted in state of the art performance on learning to play all games in a set of 57 diverse Atari games. Excitingly, our method learned a single trained policy - with a single set of weights - that exceeds median human performance. To our knowledge, this was the first time a single agent surpassed human-level performance on this multi-task domain. The same approach also demonstrated state of the art performance on a set of 30 tasks in the 3D reinforcement learning platform DeepMind Lab.

Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state of the art performance for document classification and speech recognition. In this article, we study the current state of the art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR archive) and 12 multivariate time series datasets. By training 8,730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.

Tuesday, September 11th, Rockville, MD - Today, Insilico Medicine, Inc., a Rockville-based next-generation artificial intelligence company specializing in the application of deep learning for target identification, drug discovery and aging research announces the publication of a new research paper "Entangled Conditional Adversarial Autoencoder for de-novo Drug Discovery" in Molecular Pharmaceutics, the leading American Chemical Society journal covering research on the molecular mechanistic understanding of drug delivery and drug delivery systems. The authors presented an original deep neural network architecture, Entangled Conditional Adversarial Autoencoder (ECAAE), which generates molecular structures based on various properties such as activity against a specific protein, solubility, and ease of synthesis. ECAAE was used to generate a novel inhibitor of Janus Kinase 3 (JAK3), implicated in rheumatoid arthritis, psoriasis, and vitiligo. The discovered molecule was tested in vitro and demonstrated high activity and selectivity. Generative Adversarial Networks (GANs) proposed by Ian Goodfellow and colleagues in 2014 and commonly referred to as AI imagination, are among the most exciting areas of AI research.

Deep learning is a subfield of machine learning and it comprises several approaches to tackling the single most important goal of AI research: allowing computers to model our world well enough to exhibit something like what we humans call intelligence. On a basic conceptual level, deep learning approaches share a very basic trait. DL algorithms interpret the raw data through multiple processing layers. Each of these layers takes the output of the previous one as its input and creates a more abstract representation of it. As a result, the more data is being fed into the right algorithm, the more general are the rules and features that it's able to infer in relation to a given scenario and, therefore, the apter it gets at handling new, similar situations.

Today marks the start of the fall Strata Data Conference in New York City, which has traditionally been the big data community's biggest show of the year. It's been a wild ride for the big data crowd in 2018, one that's brought its share of highs and lows. Now it's worth taking some time to consider where big data has come, and where it's possibly headed in the future. Here are five things to keep in mind as the Strata Data Conference kicks off. We've said this before, but it bears repeating: Hadoop is just one of many technologies angling for relevance in today's increasingly heterogeneous at-scale computing environment.

You seem to come across the term'Deep Learning' everywhere these days. It's all pervasive and seems to be at the heart of all AI related research. It has even spawned new and never-thought-of-before innovations! But how can you learn it? There are way too many resources out there, spread in a very unstructured and not a very beginner friendly manner.

By 2020, 85% of all customer service interactions will be handled without a human agent. As rapid advancements in technology continue transforming how businesses are developed in the modern world, entrepreneurs are actively exploring smarter ways to operate more efficiently and eliminate issues that have traditionally plagued progress and performance. From enterprise apps that make it easier to track real-time insights and manage customer relationships, to emerging tools that allow clearer communication between teams and a streamlined exchange of data -- one of the most important decisions startup founders face today is selecting the right software. As a result, the average small business is accustomed to integrating a wide range of cloud-based apps to address a complex array of business needs. In 2016, small businesses spent over $55 billion on these cloud-based services, with the average professional using between 10-16 apps daily.