It's a big day for Microsoft, which announced a slew of updates across virtually all of its product lines at its Ignite conference today. Unsurprisingly, one theme this year is artificial intelligence and machine learning. Microsoft is launching new tools to bring its Cortana assistant to the enterprise, but there is also a number of other developer-centric updates and products launching today. One of those is an update to the Azure Machine Learning services, the company's platform for letting anyone build and train machine learning models with a focus on prediction. With today's update, this platform is getting a new tool that automates much of the time-consuming selection, testing and tweaking as necessary to build a solid model.

The AI-powered document and data abstraction company has announced it is entering the Non-Performing Loan (NPL) market, though a partnership with 8G Capital Partners. Leverton will support both buyers and sellers of NPL portfolios, using artificial intelligence to conduct due diligence and closing transactions, as well as post-acquisition portfolio management. NPL transactions are highly complex and involve myriads of documents, ranging from loan agreements to security documents and collateral documentation such as title deeds, planning permits, plans. However, many transactions are still being brought to the market without complete knowledge of what each portfolio entails. Leverton said its deep learning technology can be trained to automatically identify and extract relevant information from various types of documents and contracts including loan agreements and collateral documents in over 30 languages.

This article follows my previous one on Bayesian probability & probabilistic programming that I published few months ago on LinkedIn. And for the purpose of this article, I am going to assume that most this article readers have some idea what a Neural Network or Artificial Neural Network is. Neural Network is a non-linear function approximator. We can think of it as a parameterized function where the parameters are the weights & biases of Neural Network through which we will be typically passing our data (inputs), that will be converted to a probability between 0 and 1, to some kind of non-linearity such as a sigmoid function and help make our predictions or estimations. These non-linear functions can be composed together hence Deep Learning Neural Network with multiple layers of this function compositions.

A Mars rover roaming the red planet cannot whip out a smartphone to check its location based on GPS. Instead, the robotic explorer must take panoramic pictures of the surrounding landscape so that a human back on Earth can painstakingly compare the ground images with Mars satellite maps taken from above by orbiting spacecraft. Locating a Mars mission after it first touches down, using that manual process of scrutinizing landscape features and making image comparisons, can take up to 24 hours. What's more, it still requires at least thirty minutes to confirm a rover's updated location after it's on the move. But a new AI approach that trains deep learning algorithms to perform the necessary image comparisons could reduce the localization process to mere seconds.

Deep learning, computational neuroscience, and cognitive science have overlapping goals related to understanding intelligence such that perception and behaviour can be simulated in computational systems. In neuroimaging, machine learning methods have been used to test computational models of sensory information processing. Recently, these model comparison techniques have been used to evaluate deep neural networks (DNNs) as models of sensory information processing. However, the interpretation of such model evaluations is muddied by imprecise statistical conclusions. Here, we make explicit the types of conclusions that can be drawn from these existing model comparison techniques and how these conclusions change when the model in question is a DNN. We discuss how DNNs are amenable to new model comparison techniques that allow for stronger conclusions to be made about the computational mechanisms underlying sensory information processing.

Incorporation of a new knowledge into neural networks with simultaneous preservation of the previous one is known to be a nontrivial problem. This problem becomes even more complex when new knowledge is contained not in new training examples, but inside the parameters (connection weights) of another neural network. Here we propose and test two methods allowing combining the knowledge contained in separate networks. One method is based on a simple operation of summation of weights of constituent neural networks. Another method assumes incorporation of a new knowledge by modification of weights nonessential for the preservation of already stored information. We show that with these methods the knowledge from one network can be transferred into another one non-iteratively without requiring training sessions. The fused network operates efficiently, performing classification far better than a chance level. The efficiency of the methods is quantified on several publicly available data sets in classification tasks both for shallow and deep neural networks.

We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a two-player zero-sum game. In this new formulation, both players simultaneously play the same game, where one player chooses a classifier that minimizes a classification loss whilst the other player creates an adversarial perturbation that increases the same loss when applied to every sample in the training set. By observing that performing a classification (respectively creating adversarial samples) is the best response to the other player, we propose a novel extension of a game-theoretic algorithm, namely fictitious play, to the domain of training robust classifiers. Finally, we empirically show the robustness and versatility of our approach in two defence scenarios where universal attacks are performed on several image classification datasets -- CIFAR10, CIFAR100 and ImageNet.

Glioblastoma Multiforme is a high grade, very aggressive, brain tumor, with patients having a poor prognosis. Lower grade gliomas are less aggressive, but they can evolve into higher grade tumors over time. Patient management and treatment can vary considerably with tumor grade, ranging from tumor resection followed by a combined radio- and chemotherapy to a "wait and see" approach. Hence, tumor grading is important for adequate treatment planning and monitoring. The gold standard for tumor grading relies on histopathological diagnosis of biopsy specimens. However, this procedure is invasive, time consuming, and prone to sampling error. Given these disadvantages, automatic tumor grading from widely used MRI protocols would be clinically important, as a way to expedite treatment planning and assessment of tumor evolution. In this paper, we propose to use Convolutional Neural Networks for predicting tumor grade directly from imaging data. In this way, we overcome the need for expert annotations of regions of interest. We evaluate two prediction approaches: from the whole brain, and from an automatically defined tumor region. Finally, we employ interpretability methodologies as a quality assurance stage to check if the method is using image regions indicative of tumor grade for classification.

Procedural Level Generation via Machine Learning (PLGML), the study of generating game levels with machine learning, has received a large amount of recent academic attention. For certain measures these approaches have shown success at replicating the quality of existing game levels. However, it is unclear the extent to which they might benefit human designers. In this paper we present a framework for co-creative level design with a PLGML agent.

The Knowledge graph (KG) uses the triples to describe the facts in the real world. It has been widely used in intelligent analysis and understanding of big data. In constructing a KG, especially in the process of automation building, some noises and errors are inevitably introduced or much knowledges is missed. However, learning tasks based on the KG and its underlying applications both assume that the knowledge in the KG is completely correct and inevitably bring about potential errors. Therefore, in this paper, we establish a unified knowledge graph triple trustworthiness measurement framework to calculate the confidence values for the triples that quantify its semantic correctness and the true degree of the facts expressed. It can be used not only to detect and eliminate errors in the KG but also to identify new triples to improve the KG. The framework is a crisscrossing neural network structure. It synthesizes the internal semantic information in the triples and the global inference information of the KG to achieve the trustworthiness measurement and fusion in the three levels of entity-level, relationship-level, and KG-global-level. We conducted experiments on the common dataset FB15K (from Freebase) and analyzed the validity of the model's output confidence values. We also tested the framework in the knowledge graph error detection or completion tasks. The experimental results showed that compared with other models, our model achieved significant and consistent improvements on the above tasks, further confirming the capabilities of our model.