Answering simple questions over knowledge graphs is a well-studied problem in question answering. Previous approaches for this task built on recurrent and convolutional neural network based architectures that use pretrained word embeddings. It was recently shown that finetuning pretrained transformer networks (e.g. BERT) can outperform previous approaches on various natural language processing tasks. In this work, we investigate how well BERT performs on SimpleQuestions and provide an evaluation of both BERT and BiLSTM-based models in datasparse scenarios.

We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed. Our experimental evaluation shows that our deep reinforcement learning based agents outperform two existing well-known negotiation strategies in one-to-many concurrent bilateral negotiations for a range of e-market settings.

Several deep neural network approaches have been proposed to model the task in an end-to-end fashion. Whereas the task is grounded in visual processing, if the question focuses on events described by verbs, the language understanding component becomes crucial. Our hypothesis is that models should be aware of verb semantics, as expressed via semantic role labels, argument types, and/or frame elements. Unfortunately, no VQA dataset exists that includes verb semantic information. Our first contribution is a new VQA dataset (imSituVQA) that we built by taking advantage of the imSitu annotations. The imSitu dataset consists of images manually labeled with semantic frame elements, mostly taken from FrameNet. Second, we propose a multitask CNN-LSTM VQA model that learns to classify the answers as well as the semantic frame elements. Our experiments show that semantic frame element classification helps the VQA system avoid inconsistent responses and improves performance.

Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations Patrick Schramowski, Wolfgang Stammer, Stefano Teso, Anna Brugger, Franziska Herbert, Xiaoting Shao, Hans-Georg Luigs Anne-Katrin Mahlein & Kristian Kersting Abstract Deep neural networks have shown excellent performances in many real-world applications. Unfortunately, they may show "Clever Hans"-like behavior--making use of confounding factors within datasets--to achieve high performance. In this work we introduce the novel learning setting of explanatory interactive learning (XIL) and illustrate its benefits on a plant phenotyping research task. XIL adds the scientist into the training loop such that she interactively revises the original model via providing feedback on its explanations. Our experimental results demonstrate that XIL can help avoiding Clever Hans moments in machine learning and encourages (or discourages, if appropriate) trust into the underlying model. Imagine a plant phenotyping team attempting to characterize crop resistance to plant pathogens. The plant physiologist records a larger amount of hyperspectral imaging data. Impressed by the results of deep learning in other scientific areas, she wants to establish similar results for phenotyping. Consequently, she asks a machine learning expert to apply deep learning to analyze the data. Luckily, the resulting predictive accuracy is very high. The plant physiologist, however, remains skeptical. The results are "too good, to be true". Checking the decision process of the deep model using explainable artificial intelligence (AI), the machine learning expert is flabbergasted to find that the learned deep model uses clues within the data that do not relate to the biological problem at hand, so-called confounding factors. The physiologist loses trust in AI and turns away from it, proclaiming it to be useless. Indeed, the seminal paper of Lapuschkin et al. [3] helps in "unmasking Clever Hans predictors and assessing what machines really learn". However, rather than proclaiming, as the plant physiologist might, that the machines have learned the right predictions for wrong reasons and can therefore not be trusted, we here showcase that interactions between the learning system and the human user can correct the model towards making the right predictions for the right reasons. This may also increase the trust in machine learning models.

Building on the rampant popularity of Python was always going to be a good idea for the Facebook-born PyTorch, an open source machine learning framework. Just how good of an idea, however, few could have guessed. That's because no matter how many things you get right when launching an open source project (great docs, solid technical foundation, etc.), there is always an element of luck to a project's success. Well, consider PyTorch lucky, then. Because it's booming and, if analyst Thomas Dinsmore is to be believed, "By the end of [2020] PyTorch will have more active contributors than TensorFlow."

The eye disease diabetic retinopathy is the fastest growing cause of blindness in the world. There are over 100 million people in the world with diabetes and ideally, they would be screened each year for this degenerative eye condition. It is fully treatable if caught early, however if it's not detected you could suffer partial or full vision loss. They look for scattered hemorrhages and micro-aneurysms to grade the image. This is quite subjective in that a grade of two (2) means come back in a year and a grade of three (3) means come to the clinic right away.

Keras is an open source Neural Network library written in Python that runs on top of Theano or TensorFlow. It is an API designed for human beings, not machines, and keeping that in mind it minimizes the number of user actions required for common use cases, and provides clear and actionable feedback on encountering user error. Keras neural network library is designed to be modular, fast and easy to learn and use. It offers a higher-level, more intuitive set of abstractions that make it easy to develop deep learning models regardless of the computational backend used. Developers can use Keras to quickly build neural networks without worrying about the mathematical aspects of tensor algebra, numerical techniques, and optimization methods, making it developer-friendly. Being modular in nature, it is flexible and apt for innovative research.

Players applaud, say words like Whoo, bang plastic knives on the table and enjoy the best weekends with artificial intelligence as the main act, thanks to AI unleashed in games. WIRED UK's science editor, Matt Reynolds, looked at DeepMind's impact on AI milestones: "It has outplayed Go champions, bested professional StarCraft players and turned its attention to chess and shogi." Let the games continue but the serious stuff must seriously shine. In brief, we can admire that unleashing AI for the purpose of scientific discovery has become especially alive and well thanks to research at DeepMind. Tech watchers commented this week on research papers showing the strengths of AI. "As AI matures as a field (and runs out of video games to conquer) probably more of its achievements will look like these: solid improvements in important research domains."

Interpreting 3D seismic data correctly helps identify geological features that may hold or trap oil and gas deposits. In this post, I use these services to build and train a custom deep-learning model for the interpretation of geological features on 3D seismic data. The purpose of this post is to show oil and gas data scientists how they can quickly and easily create customized semantic-segmentation models. Amazon SageMaker is a fully managed service that enables data scientists to build, train, tune, and deploy machine learning models at any scale. This service provides a powerful and scalable compute environment that is also easy to use.