Clustering of time series data exhibits a number of challenges not present in other settings, notably the problem of registration (alignment) of observed signals. Typical approaches include pre-registration to a user-specified template or time warping approaches which attempt to optimally align series with a minimum of distortion. For many signals obtained from recording or sensing devices, these methods may be unsuitable as a template signal is not available for pre-registration, while the distortion of warping approaches may obscure meaningful temporal information. We propose a new method for automatic time series alignment within a convex clustering problem. Our approach, Temporal Registration using Optimal Unitary Transformations (TROUT), is based on a novel distance metric between time series that is easy to compute and automatically identifies optimal alignment between pairs of time series. By embedding our new metric in a convex formulation, we retain well-known advantages of computational and statistical performance. We provide an efficient algorithm for TROUT-based clustering and demonstrate its superior performance over a range of competitors.

Predicting the dynamics of neural network parameters during training is one of the key challenges in building a theoretical foundation for deep learning. A central obstacle is that the motion of a network in high-dimensional parameter space undergoes discrete finite steps along complex stochastic gradients derived from real-world datasets. We circumvent this obstacle through a unifying theoretical framework based on intrinsic symmetries embedded in a network's architecture that are present for any dataset. We show that any such symmetry imposes stringent geometric constraints on gradients and Hessians, leading to an associated conservation law in the continuous-time limit of stochastic gradient descent (SGD), akin to Noether's theorem in physics. We further show that finite learning rates used in practice can actually break these symmetry induced conservation laws. We apply tools from finite difference methods to derive modified gradient flow, a differential equation that better approximates the numerical trajectory taken by SGD at finite learning rates. We combine modified gradient flow with our framework of symmetries to derive exact integral expressions for the dynamics of certain parameter combinations. We empirically validate our analytic predictions for learning dynamics on VGG-16 trained on Tiny ImageNet. Overall, by exploiting symmetry, our work demonstrates that we can analytically describe the learning dynamics of various parameter combinations at finite learning rates and batch sizes for state of the art architectures trained on any dataset. Just like the fundamental laws of classical and quantum mechanics taught us how to control and optimize the physical world for engineering purposes, a better understanding of the laws governing neural network learning dynamics can have a profound impact on the optimization of artificial neural networks.

Japan is seeking to boost its flagging birth rate by funding the use of artificial intelligence to help match lonely hearts, an official said Monday. Although it might not conjure thoughts of romance, AI tech can match a wider and smarter range of potential suitors, the Cabinet official said. Prime Minister Yoshihide Suga's government plans to allocate ¥2 billion ($19 million) in the next fiscal year to back local authorities that run programs to help their residents find love, he said. Around half of the nation's 47 prefectures offer matchmaking services and some of them have already introduced AI systems, according to the Cabinet Office. The human-run matchmaking services often use standardized forms to list people's interests and hobbies, and AI systems can perform more advanced analysis of this data.

Japan is seeking to boost its flagging birthrate by funding the use of artificial intelligence to help match lonely hearts, an official said Monday. Although it might not conjure thoughts of romance, AI tech can match a wider and smarter range of potential suitors, the cabinet official told AFP. Prime Minister Yoshihide Suga's government plans to allocate two billion yen ($19 million) in the next fiscal year to back local authorities that run schemes to help their residents find love, he said. Around half of the nation's 47 prefectures offer matchmaking services and some of them have already introduced AI systems, according to the cabinet office. The human-run matchmaking services often use standardised forms to list people's interests and hobbies, and AI systems can perform more advanced analysis of this data.

In October, his firm announced it had won a contract to install facial recognition access control systems at two US Air Force bases - a move designed specifically to reduce contact between people at the bases, for example, via touchpads and surfaces. Mr Moore thinks venues open to the public, including sports stadiums, will also turn to "contactless" identify verification.

Since antiquity once a weapon was developed there were soon methods to counter it. Just as the shield and armor were meant to protect a soldier from swords and spears, today there are now countermeasures designed to stop smart munitions, which were first developed during the Second World War. While the United States has continued to develop even smarter bombs, including laser- and GPS-guided bombs, the latest efforts include those that could select targets automatically when dropped from an aircraft. Such smart munitions could maneuver in flight after being launched, but efforts have continued to counter such measures and this has included the use of jamming technology. In what is part of a seemingly never-ending "arms race," Russia is now reportedly developing software that is designed for use in precision munitions of defensive and offensive weapons.

The Indian Air Force has taken a big step towards developing indigenous'Swarm Drone' technology which uses artificial intelligence to enhance its combat capability. On Saturday, the IAF shared pictures of swarm drone tests on its official Twitter handle, with the caption: "IAF is leading the way in using Artificial Intelligence to add to its combat potential. Swarm drones is a prime example." Swarm drones is a prime example. Testing of Swarm Drone technology is a major achievement for India.

Near the end of the Georgia Senate runoff debate Sunday night, moderators asked Sen. Kelly Loeffler, who was ultimately cleared in her insider trading investigation earlier this year, whether members of Congress should be barred from trading stocks. "What's at stake here, in this election, is the American Dream." Loeffler is trying to grind out a win against Rev. Raphael Warnock more on the strength of QAnon than on that of the suburban women whom Gov. Brian Kemp felt she could appeal to when he appointed her earlier this year to the seat left empty by the retirement of Sen. Johnny Isakson. She has nothing to offer the center, now, other than parodic--which isn't to say "unsuccessful"--efforts to slam her opponent as a radical communist who wants to defund the police. Her debate performance Sunday night was more a mockery of this medium of voter-informing than the legendary train-wreck of a first debate between Donald Trump and Joe Biden in September.

Fifteen UK researchers have been awarded the Fellowships, named after AI pioneer Alan Turing, supported by a £20million government investment. As a result of the government investment, Fellows will work with academia and industry to help elevate their world-class research and transfer their innovations from the lab to the real world. These innovations have the potential to change how people live, work and communicate, helping to place the UK at the forefront of the AI and data revolution. Dr Hernandez Lobato's research focus will be on'Machine Learning for Molecular Design'. Many existing challenges, from personalised health care to energy production and storage, require the design and manufacture of new molecules.

In this paper, the publicly available dataset of condition based maintenance of combined diesel-electric and gas (CODLAG) propulsion system for ships has been utilized to obtain symbolic expressions which could estimate gas turbine shaft torque and fuel flow using genetic programming (GP) algorithm. The entire dataset consists of 11934 samples that was divided into training and testing portions of dataset in an 80:20 ratio. The training dataset used to train the GP algorithm to obtain symbolic expressions for gas turbine shaft torque and fuel flow estimation consisted of 9548 samples. The best symbolic expressions obtained for gas turbine shaft torque and fuel flow estimation were obtained based on their $R^2$ score generated as a result of the application of the testing portion of the dataset on the aforementioned symbolic expressions. The testing portion of the dataset consisted of 2386 samples. The three best symbolic expressions obtained for gas turbine shaft torque estimation generated $R^2$ scores of 0.999201, 0.999296, and 0.999374, respectively. The three best symbolic expressions obtained for fuel flow estimation generated $R^2$ scores of 0.995495, 0.996465, and 0.996487, respectively.