We present a sparse representation of model uncertainty for Deep Neural Networks (DNNs) where the parameter posterior is approximated with an inverse formulation of the Multivariate Normal Distribution (MND), also known as the information form. The key insight of our work is that the information matrix, i.e. the inverse of the covariance matrix tends to be sparse in its spectrum. Therefore, dimensionality reduction techniques such as low rank approximations (LRA) can be effectively exploited. To achieve this, we develop a novel sparsification algorithm and derive a cost-effective analytical sampler. As a result, we show that the information form can be scalably applied to represent model uncertainty in DNNs. Our exhaustive theoretical analysis and empirical evaluations on various benchmarks show the competitiveness of our approach over the current methods.

A second burst of interest in AI authorship broke out in the mid-1980s. Congress once again commissioned a study, this time from its Office of Technology Assessment (OTA), to address this and other controversial computer-related issues. OTA did not offer an answer to the question, perhaps in part because at that time, it was a "toy problem" because no commercially significant outputs of AI or other software programs had yet been generated.5 But deep learning and other AI breakthroughs have caused IP professionals to rethink the AI authorship issue.1,2 For example, The Next Rembrandt video features a group of art experts and computer scientists discussing how they collaborated to digitize many Rembrandt paintings, develop models of particular features of the paintings, and then create a Rembrandt-like portrait of a man with facial hair wearing a hat and looking to the right.6 The resulting AI-generated painting really does look like a Rembrandt.

GlobalData research has found the top artificial intelligence (AI) influencers based on their performance and engagement online. Using research from GlobalData's Influencer platform, Verdict has named ten of the most influential people in artificial intelligence on Twitter during May 2020. Ronald van Loon is a recognised thought leader in technologies including AI, big data, IoT, machine learning, deep learning, 5G, predictive analytics, cloud, edge and data science. He currently serves as principal analyst and CEO of the Intelligent World, an influencer network that connects experts, businesses, and influencers to new audiences, helping them collaborate, create and share diverse content. Loon is of the opinion that AI has progressed at a furious pace over the past few years, and though it has usurped large chunks of the big data, the technology is nowhere near human intelligence.

Marrying topic models and language models exposes language understanding to a broader source of document-level context beyond sentences via topics. While introducing topical semantics in language models, existing approaches incorporate latent document topic proportions and ignore topical discourse in sentences of the document. This work extends the line of research by additionally introducing an explainable topic representation in language understanding, obtained from a set of key terms correspondingly for each latent topic of the proportion. Moreover, we retain sentence-topic associations along with document-topic association by modeling topical discourse for every sentence in the document. We present a novel neural composite language model that exploits both the latent and explainable topics along with topical discourse at sentence-level in a joint learning framework of topic and language models. Experiments over a range of tasks such as language modeling, word sense disambiguation, document classification, retrieval and text generation demonstrate ability of the proposed model in improving language understanding.

Robustness of neural networks has recently attracted a great amount of interest. The many investigations in this area lack a precise common foundation of robustness concepts. Therefore, in this paper, we propose a rigorous and flexible framework for defining different types of robustness that also help to explain the interplay between adversarial robustness and generalization. The different robustness objectives directly lead to an adjustable family of loss functions. For two robustness concepts of particular interest we show effective ways to minimize the corresponding loss functions. One loss is designed to strengthen robustness against adversarial off-manifold attacks, and another to improve generalization under the given data distribution. Empirical results show that we can effectively train under different robustness objectives, obtaining higher robustness scores and better generalization, for the two examples respectively, compared to the state-of-the-art data augmentation and regularization techniques.

Graph neural networks have attracted wide attentions to enable representation learning of graph data in recent works. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical representation of graph data. However, most recent graph pooling methods still fail to efficiently exploit the geometry of graph data. In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Node proximity is obtained by harmonizing the kernel representation of topology information and node features. Implicit structure-aware kernel representation of topology information allows efficient graph pooling without explicit eigendecomposition of the graph Laplacian. Similarities of node signals are adaptively evaluated with the combination of the affine transformation and kernel trick using the Gaussian RBF function. Experimental results demonstrate that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.

The gradient boosting machine is a powerful ensemble-based machine learning method for solving regression problems. However, one of the difficulties of its using is a possible discontinuity of the regression function, which arises when regions of training data are not densely covered by training points. In order to overcome this difficulty and to reduce the computational complexity of the gradient boosting machine, we propose to apply the partially randomized trees which can be regarded as a special case of the extremely randomized trees applied to the gradient boosting. The gradient boosting machine with the partially randomized trees is illustrated by means of many numerical examples using synthetic and real data.

Precise and reliable estimation of reference evapotranspiration (ET o ) is an essential for the irrigation and water resources management. ET o is difficult to predict due to its complex processes. This complexity can be solved using machine learning methods. This study investigates the performance of artificial neural network (ANN) and deep neural network (DNN) models for estimating daily ET o . Previously proposed ANN and DNN methods have been realized, and their performances have been compared. Six input data including maximum air temperature (T max ), minimum air temperature (T min ), solar radiation (R n ), maximum relative humidity (RH max ), minimum relative humidity (RH min ) and wind speed (U 2 ) are used from 4 meteorological stations (Adana, Aksaray, Isparta and Ni\u{g}de) during 1999-2018 in Turkey. The results have shown that our proposed DNN models achieves satisfactory accuracy for daily ET o estimation compared to previous ANN and DNN models. The best performance has been observed with the proposed model of DNN with SeLU activation function (P-DNN-SeLU) in Aksaray with coefficient of determination (R 2 ) of 0.9934, root mean square error (RMSE) of 0.2073 and mean absolute error (MAE) of 0.1590, respectively. Therefore, the P-DNN-SeLU model could be recommended for estimation of ET o in other climate zones of the world.

What could your company achieve with the worlds most advanced robot dog working for you? One of New Zealand's leading Artificial Intelligence development companies, AwareGroup has secured a partnership deal with the operations arm of Boston Dynamics. Rocos Robotics Platform and AwareGroup will work together to provide five New Zealand companies with the opportunity to develop and deploy SPOT robots for any number of practical use-cases. Inspect progress on construction sites, create digital twins, and identify hazards. Remotely inspect and identify supporting awareness and operations.

A 30ft-long whale that died after it became stranded in a Welsh estuary was a one-year-old male calf that was struggling to find food, an autopsy has revealed. The fin whale, named Henry by rescuers, is thought to have been recently weaned by his mother and started to live independently - as they stop receiving milk at around six to seven months old - before becoming beached. The young male died on the sands of the Dee Estuary, North Wales, on June 14. He had beached at least twice over the previous two days. A post-mortem was carried out by the Cetacean Strandings Investigation Programme (CSIP) to identify the cause of death and find out why the whale ended up out of the sea.