Automatic article commenting is helpful in encouraging user engagement and interaction on online news platforms. However, the news documents are usually too long for traditional encoder-decoder based models, which often results in general and irrelevant comments. In this paper, we propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph. By organizing the article into graph structure, our model can better understand the internal structure of the article and the connection between topics, which makes it better able to understand the story. We collect and release a large scale news-comment corpus from a popular Chinese online news platform Tencent Kuaibao. Extensive experiment results show that our model can generate much more coherent and informative comments compared with several strong baseline models.

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining logic and constraint reasoning with stochastic-gradient-based neural network optimization. We illustrate the power of DRNets on de-mixing overlapping hand-written Sudokus (Multi-MNIST-Sudoku) and on a substantially more complex task in scientific discovery that concerns inferring crystal structures of materials from X-ray diffraction data under thermodynamic rules (Crystal-Structure-Phase-Mapping). At a high level, DRNets encode a structured latent space of the input data, which is constrained to adhere to prior knowledge by a reasoning module. The structured latent encoding is used by a generative decoder to generate the targeted output. Finally, an overall objective combines responses from the generative decoder (thinking fast) and the reasoning module (thinking slow), which is optimized using constraint-aware stochastic gradient descent. We show how to encode different tasks as DRNets and demonstrate DRNets' effectiveness with detailed experiments: DRNets significantly outperform the state of the art and experts' capabilities on Crystal-Structure-Phase-Mapping, recovering more precise and physically meaningful crystal structures. On Multi-MNIST-Sudoku, DRNets perfectly recovered the mixed Sudokus' digits, with 100% digit accuracy, outperforming the supervised state-of-the-art MNIST de-mixing models. Finally, as a proof of concept, we also show how DRNets can solve standard combinatorial problems -- 9-by-9 Sudoku puzzles and Boolean satisfiability problems (SAT), outperforming other specialized deep learning models. DRNets are general and can be adapted and expanded to tackle other tasks.

Visual navigation in complex environments is inefficient with traditional reactive policy or general-purposed recurrent policy. To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module. The memory construction module builds the topological graph based on supervised learning by taking the exploration prior. Then, guided attention features are extracted with the graph attention module. Finally, the deep reinforcement learning based control module makes decisions based on visual observations and guided attention features. Detailed convergence analysis of GAM is presented in this paper. We evaluate GAM-based navigation system in two complex 3D environments. Experimental results show that the GAM-based navigation system significantly improves learning efficiency and outperforms all baselines in average success rate.

We consider the problem of generating plausible and diverse video sequences, when we are only given a start and an end frame. This task is also known as inbetweening, and it belongs to the broader area of stochastic video generation, which is generally approached by means of recurrent neural networks (RNN). In this paper, we propose instead a fully convolutional model to generate video sequences directly in the pixel domain. We first obtain a latent video representation using a stochastic fusion mechanism that learns how to incorporate information from the start and end frames. Our model learns to produce such latent representation by progressively increasing the temporal resolution, and then decode in the spatiotemporal domain using 3D convolutions. The model is trained end-to-end by minimizing an adversarial loss. Experiments on several widely-used benchmark datasets show that it is able to generate meaningful and diverse in-between video sequences, according to both quantitative and qualitative evaluations.

Recently we have discussed the emerging concept of smart farming that makes agriculture more efficient and effective with the help of high-precision algorithms. The mechanism that drives it is Machine Learning -- the scientific field that gives machines the ability to learn without being strictly programmed. It has emerged together with big data technologies and high-performance computing to create new opportunities to unravel, quantify, and understand data intensive processes in agricultural operational environments. Let's discover how agriculture can benefit from Machine Learning at every stage: Our favorite, this application is so logical and yet so unexpected, because mostly you read about harvest prediction or ambient conditions management at later stages. Species selection is a tedious process of searching for specific genes that determine the effectiveness of water and nutrients use, adaptation to climate change, disease resistance, as well as nutrients content or a better taste.

If you are new to Data Science, it is possible that you have seen the three buzzwords being used time and again (often, interchangeably but mistakenly). So, what is the difference? In short, each of them is a subset of the earlier. Let's begin by understanding each of them separately. AI refers to the intelligence exhibited by machines (like, problem solving and learning) using techniques or algorithms like search, logic, if-then rules, decision trees and machine learning (including deep learning).

In the machine learning and deep learning paradigm, model "parameters" and "hyperparameters" are two frequently used terms where "parameters" define configuration variables that are internal to the model and whose values can be estimated from the training data and "hyperparameters" define configuration variables that are external to the model and whose values cannot be estimated from the training data (What is the Difference Between a Parameter and a Hyperparameter? Thus, the hyperparameter values need to be manually assigned by the practitioner. Every machine learning and deep learning model that we make has a different set of hyperparameter values that need to be fine-tuned to be able to obtain a satisfactory result. Compared to machine learning models, deep learning models tend to have a larger number of hyperparameters that need optimizing in order to get the desired predictions due to its architectural complexity over typical machine learning models. Repeatedly experimenting with different value combinations manually to derive the optimal hyperparameter values for each of these hyperparameters can be a very time consuming and tedious task that requires good intuition, a lot of experience, and a deep understanding of the model. Moreover, some hyperparameter values may require continuous values, which will have an undefined number of possibilities, and even if the hyperparameters require a discrete value, the number of possibilities is enormous, thus manually performing this task is rather difficult.

Reinforcement learning has traditionally occupied a niche status in the world of artificial intelligence. But reinforcement learning has started to assume a larger role in many AI initiatives in the past few years. Its application sweet spot is in calculation of optimal actions to be taken by agents in environmentally contextualized decision scenarios. Using trial-and-error approaches to maximize an algorithmic reward function, reinforcement learning is well suited to many adaptive-control and multiagent automation applications in IT operations management, energy, health care, commerce, finance, transportation, and finance. And it's being used to train the AI that powers both its traditional focus areas--robotics, gaming, and simulation--and a new generation of AI solutions in edge analytics, natural language processing, machine translation, computer vision, and digital assistants.

Deep learning has revolutionized the machine understanding of imagery. Yet today's image recognition models are still limited by the availability of large annotated training datasets upon which to build their libraries of recognized objects and activities. To address this, Google's Vision AI API expands its native catalog of around 10,000 visually recognized objects and activities with the ability to perform the equivalent of a reverse Google Images search across the open Web and tally up the top topics used to caption the given image everywhere it has previously appeared, lending unprecedentedly rich context and understanding, even yielding unique labels for breaking news events. What might this process yield for a week of television news? Google's Vision AI API represents a unique hybrid between traditional deep learning-based image labeling based on a library of previously trained models and the ability to leverage the open Web to annotate images based on the most common topics visually similar images are captioned with. Using its Web Entities feature, the Vision AI API performs what amounts to a reverse Google Images search over the open Web, identifying images across the entire Web that look most similar to the given image.

Inequality may seem something that is all too evident, as run down streets and communities show visible signs of lacking due care and attention, But in many communities, poverty can lie out of plain sight. New research from Imperial College London suggests deep learning can be used to better detect social, economic, environmental, and health inequalities than existing methods. The researchers believe their system can help policymakers gain a greater understanding of the inequalities that exist within their city, and therefore have more informed policies for tackling them. What's more, the real-time nature of the metrics allows more effective interventions to be crafted. The team's deep learning-based system was trained on publicly available street view images from London, Birmingham, Manchester, and Leeds combined with government statistics.