Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the solution of the inverse problem is significantly influenced by both. Current IRL approaches assume that if the transition model is unknown, additional samples from the system's dynamics are accessible, or the observed behavior provides enough samples of the system's dynamics to solve the inverse problem accurately. These assumptions are often not satisfied. To overcome this, we present a gradient-based IRL approach that simultaneously estimates the system's dynamics. By solving the combined optimization problem, our approach takes into account the bias of the demonstrations, which stems from the generating policy. The evaluation on a synthetic MDP and a transfer learning task shows improvements regarding the sample efficiency as well as the accuracy of the estimated reward functions and transition models.

A BSTRACT Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform. However, this leads to an extensive increase in the computational complexity of the training procedure. We present a novel, parameterizable transfer function based on the mathematical concept of non-integer functional iteration that allows the operation each neuron performs to be smoothly and, most importantly, differentiablely adjusted between addition and multiplication. This allows the decision between addition and multiplication to be integrated into the standard backpropagation training procedure. The value of such a product unit is given byy i σ ( j x W ij j).

In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase in the number of classes comes along with increased ambiguity between the class labels, raising the question if top-1 error is the right performance measure. In this paper, we provide an extensive comparison and evaluation of established multiclass methods comparing their top-k performance both from a practical as well as from a theoretical perspective. Moreover, we introduce novel top-k loss functions as modifications of the softmax and the multiclass SVM losses and provide efficient optimization schemes for them. In the experiments, we compare on various datasets all of the proposed and established methods for top-k error optimization. An interesting insight of this paper is that the softmax loss yields competitive top-k performance for all k simultaneously. For a specific top-k error, our new top-k losses lead typically to further improvements while being faster to train than the softmax.

Noname manuscript No. (will be inserted by the editor) Abstract Hierarchical models are versatile tools for joint modeling of data sets arising from different, but related, sources. Fully Bayesian inference may, however, become computationally prohibitive if the sourcespecific data models are complex, or if the number of sources is very large. To facilitate computation, we propose an approach, where inference is first made independently for the parameters of each data set, whereupon the obtained posterior samples are used as observed data in a substitute hierarchical model, based on a scaled likelihood function. Compared to direct inference in a full hierarchical model, the approach has the advantage of being able to speed up convergenceby breaking down the initial large inference problem into smaller individual subproblems with better convergence properties. Moreover it enables parallel processing of the possibly complex inferences of the source-specific parameters, which may otherwise create a computational bottleneck if processed jointly as part of a hierarchical model.

In this blog post, we will use Hivemall, the open source Machine Learning-on-SQL library available in the Treasure Data environment, to introduce the basics of machine learning. We will use an E-Commerce dataset from Kaggle, the data science competition platform. The first challenge is predicting the retail sales for the Rossman stores (the full details at Kaggle). We will use an ensemble learning technique known as Random Forest regression. Rossman is a pharmacy chain with over 3,000 stores in seven countries within Europe.

Sensitive details held by police and prosecutors in England are being lost because evidence is still being shared on computer discs, watchdogs say. Police and prosecution watchdogs looked at criminal justice computer systems and found the testimonies of underage and vulnerable victims and witnesses had been kept on portable discs. In one case a DVD interview of a 12-year-old sex offence victim was lost. The CPS said it and the police were reviewing their handling of such data. The joint report from HM Crown Prosecution Service Inspectorate and HM Inspectorate of Constabulary said there was a "widespread issue" involving the Crown Prosecution Service (CPS) "misplacing discs containing sensitive evidence and information".

The marriage of computing power and data is finally bearing fruit in the field of cognitive computing, sometimes called machine learning or, more controversially, artificial intelligence. In its most everyday form, we see it in tools such as Google Translate or Microsoft's Bing Translate, which can translate phrases and documents effortlessly across multiple languages. More futuristically, the promise of self-driving vehicles, which can complete entire road journeys without driver intervention, is already being realised. Yet the biggest revolution in work is happening at some of the most basic levels, such as reading and dissecting legal documents to extract meaning and useful information. The tedious slog of work can be transformed by computers which are able to read and parse legal phrases, and summarise them or enter relevant details into a database or spreadsheet.

Jon Barker: Jon Barker is a Solution Architect with NVIDIA, helping customers and partners develop applications of GPU-accelerated machine learning and data analytics to solve defense and national security problems. He is particularly focused on applications of the rapidly developing field of deep learning. Prior to joining NVIDIA, Jon spent almost a decade as a government research scientist within the U.K. Ministry of Defence and the U.S. Department of Defense R&D communities. While in government service, he led R&D projects in sensor data fusion, big data analytics, and machine learning for multi-modal sensor data to support military situational awareness and aid decision making. He has a Ph.D. and B.Sc. in Pure Mathematics from the University of Southampton, U.K.

This week, in Geneva, Indian diplomats are closely monitoring an international expert review of the legal implications of the so-called "lethal autonomous weapons". These weapons will have the capability of selecting and engaging targets on their own. Although fully autonomous weapons are yet to register significant presence in the arsenal of any nation, many consider their development and deployment inevitable in the coming years. Rapid advances in robotics, machine-learning and big-data analytics are at once driving the so-called "fourth industrial revolution" and the transformation of modern warfare. How the leading powers mobilise and deploy these technologies will shape the balance of economic and military power among them in the coming decades.

Nvidia became famous for its graphics processing unit chips that power some of the hottest gaming personal computers. Today, Chief Executive Jen-Hsun Huang signaled that he's aiming even higher in a bid to reinvent the data center and cloud computing. The company announced a new chip and a new computers both focused on artificial intelligence, in particular the fast-rising branch called deep learning that attempts to mimic the activity on layers of neurons in the brain. The technology is the basis for recent breakthroughs in speech and image recognition, self-driving cars and other technology-driven products and services. "Our company has gone all-in on deep learning," Huang said at the Apr. 5 opening of its annual GPU Technology Conference in San Jose, where he made the announcements.