Neural Information Processing Systems http://nips.cc/

We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. We compare it with reverse dynamic method (known in literature as "adjoint method") to train neural ODEs on classification, density estimation and inference approximation tasks. We also propose a theoretical justification of our approach using logarithmic norm formalism. As a result, our method allows faster model training than the reverse dynamic method what was confirmed and validated by extensive numerical experiments for several standard benchmarks.

We propose a reinforcement learning strategy to control wind turbine energy generation by actively changing the rotor speed, the rotor yaw angle and the blade pitch angle. A double deep Q-learning with a prioritized experience replay agent is coupled with a blade element momentum model and is trained to allow control for changing winds. The agent is trained to decide the best control (speed, yaw, pitch) for simple steady winds and is subsequently challenged with real dynamic turbulent winds, showing good performance. The double deep Q- learning is compared with a classic value iteration reinforcement learning control and both strategies outperform a classic PID control in all environments. Furthermore, the reinforcement learning approach is well suited to changing environments including turbulent/gusty winds, showing great adaptability. Finally, we compare all control strategies with real winds and compute the annual energy production. In this case, the double deep Q-learning algorithm also outperforms classic methodologies.

"We started to look at the challenges current systems experienced when scaling state-of-the-art machine learning techniques for graphs to really …

Computer vision can easily distinguish between well-defined shapes, for instance, a sphere and a cube. Things go awry with less distinct forms. It's easy for the human eye to differentiate between a cat and a dog -- you know what is what. But computers have no such innate capability, and even the most advanced computer vision algorithms often mistake a cat for a dog and vice versa. Computers have to be trained rigorously to classify fuzzy objects.

"Something that is quite interesting is deep learning (or) artificial intelligence that can gather through data from different sources, images, diagnostic …

With roughly the same population as the State of Missouri, Lebanon is a small country of six million people that borders Syria and Israel. Due to its location, the country has been subjected to a multitude of political and religious factions inhabiting the state. People frequently fight over whose invisible friend is better, and the country has faced long periods of instability including wars with Israel, civil wars and internal conflicts, and most recently some spillover from the Syrian war – which means lots of Syrians flying around on motorcycles. All of this turmoil has contributed to structural problems in the economy such as chronic fiscal deficits that have increased Lebanon's debt-to-GDP ratio to the third highest in the world. Economic growth has slowed to 1-2% over the past decade which constrains government investments in necessary infrastructure improvements. Notwithstanding these challenges, day to day life in Lebanon is pretty awesome.

A month back, I participated in a Kaggle competition called TFI. I started with my first submission at 50th percentile. Having worked relentlessly on feature engineering for more than 2 weeks, I managed to reach 20th percentile. To my surprise, right after tuning the parameters of the machine learning algorithm I was using, I was able to breach top 10th percentile. This is how important tuning these machine learning algorithms are.

The new Huracán is lighter, faster, and corners like a champ - thanks to technology. Lamborghini CEO Stefano Domenicali, left, and head of research and development Maurizio Reggiani recently visited San Francisco with their Huracan Performante in tow. "This car represents so much of what we are," says Reggiani, who joined CEO Stefano Domenicali for a breakfast interview with USA TODAY Tuesday. "We are looking to the future." The future, these days, seems to be all about self-driving cars designed to completely detach the driver from the transportation experience.

FinancialForce's latest high profile hire, Fred Studer, says the more time they can give back to customers, the better. Studer is the first chief marketing officer (CMO) of cloud ERP vendor FinancialForce, joining long-time friend and mentor Tod Nielsen who was recently appointed chief executive. AccountingWEB caught up with Studer, a former Oracle, Microsoft and NetSuite executive, to find out more about his accounting roots and his future vision for FinancialForce. Studer exudes enthusiasm and marketing flair, declaring at one point in our interview his quest to "bring sexy back to accounting", but he remains rooted in accounting and helping transform and evolve finance. Studer said he was drawn to the FinancialForce role in part due to his background studying finance and accounting, and then working as a managerial accountant rising up to assistant controller.