Cross-validation of predictive models is the de-facto standard for model selection and evaluation. In proper use, it provides an unbiased estimate of a model's predictive performance. However, data sets often undergo a preliminary data-dependent transformation, such as feature rescaling or dimensionality reduction, prior to cross-validation. It is widely believed that such a preprocessing stage, if done in an unsupervised manner that does not consider the class labels or response values, has no effect on the validity of cross-validation. In this paper, we show that this belief is not true. Preliminary preprocessing can introduce either a positive or negative bias into the estimates of model performance. Thus, it may lead to sub-optimal choices of model parameters and invalid inference. In light of this, the scientific community should re-examine the use of preliminary preprocessing prior to cross-validation across the various application domains. By default, all data transformations, including unsupervised preprocessing stages, should be learned only from the training samples, and then merely applied to the validation and testing samples.

File photo - An unmanned 11-meter rigid-hull inflatable boat from Naval Surface Warfare Center Carderock operates autonomously during an Office of Naval Research-sponsored demonstration of swarmboat technology on the James River in Newport News, Va.(U.S. Navy photo by John F. Williams/Released) The U.S. Navy will launch a swarm of interconnected small attack drone boats on mock-combat missions to refine command and control technology and prepare its "Ghost Fleet" of autonomous, yet networked surface craft for war. Developed by the Office of Naval Research and Naval Sea Systems Command, "Ghost Fleet" represents a Navy strategy to surveil, counter, overwhelm and attack enemies in a coordinated fashion - all while keeping sailors on host ships at safer distances. The small boats, many of them called Unmanned Surface Vessels, are designed to conduct ISR missions, find and destroy mines and launch a range of attacks including electronic warfare and even mounted guns. The concept is to use advanced computer algorithms bringing new levels of autonomy to surface warfare, enabling ships to coordinate information exchange, operate in tandem without colliding and launch combined assaults. "Ghost Fleet is really helping us in the Command and Control and coms arena. The demonstration will allow us to learn lessons about integrated payloads with USVs," Capt.

Charles River Laboratories International, Inc. (NYSE: CRL) and Atomwise, Inc. today announced the formation of a strategic alliance that offers clients access to Atomwise's artificial intelligence (AI)-powered, structure-based, drug design technology, which allows scientists to predict how well a small molecule will bind to a target protein of interest. By removing sole reliance on empirical screening, AI enables drug researchers to test an extremely large and diverse chemical space in a matter of days and move through the optimization process quickly by focusing only on those compounds predicted to have improved target-binding attributes. This alliance combines two industry-leading drug discovery platforms: Atomwise's AI technology and Charles River's unique portfolio of end-to-end drug discovery and early-stage development capabilities and expertise. Leveraging Atomwise's AI technology and Charles River's integrated drug discovery platform has the potential to significantly streamline the hit discovery, hit-to-lead, and lead optimization process for clients' research efforts. Founded in 2012, the San Francisco Bay Area-based venture has raised over $50 million in venture capital financing.

Intuition Robotics has been working on its ElliQ "proactive social robot for older adults" for only a few years--the company, founded in 2016, has managed to secure funding from Toyota AI Ventures, Samsung, and iRobot, among others. For nearly a year, Intuition has been testing ElliQ in the homes of beta testers aged 62-97 in the San Francisco Bay Area, and things have apparently gone well enough that they've decided that the robot is ready to go on sale. If you're wondering what ElliQ actually does, the website is a bit more informative, but not much: ElliQ is specially designed with and for older adults to give them everything they need to stay sharp, connected and engaged. Interacting with ElliQ and the world is easy and fun, and through AI she becomes even more helpful by learning what you like and need. ElliQ enables family members to easily check-in with you and help with the day-to-day, creating more quality time together wherever you live. ElliQ suggests personalized activities at the right time, keeping you sharp, active and engaged.

One noninvasive way to study frog communities is by analyzing long-term samples of acoustic material containing calls. This immense task has been optimized by the development of Machine Learning tools to extract ecological information. We explored a likelihood-ratio audio detector based on Gaussian mixture model classification of 10 frog species, and applied it to estimate presence-absence in audio recordings from an actual amphibian monitoring performed at Yasun ı National Park in the Ecuadorian Amazonia. A modified filter-bank was used to extract 20 cepstral features that model the spectral content of frog calls. Experiments were carried out to investigate the hyperparameters and the minimum frog-call time needed to train an accurate GMM classifier. With 64 Gaussians and 12 seconds of training time, the classifier achieved an average weighted error rate of 0.9% on the 10-fold cross-validation for nine species classification, as compared to 3% with MFCC and 1.8% with PLP features. For testing, 10 GMMs were trained using all the available training-validation dataset to study 23.5 hours in 141, 10-minute long samples of unidentified real-world audio recorded at two frog communities in 2001 with analog equipment. To evaluate automatic presence-absence estimation, we characterized the audio samples with 10 binary variables each corresponding to a frog species, and manually labeled a subset of 18 samples using headphones. The one-vs-all Receiver Operating Characteristics curves were used to tune the likelihood-ratio detector per class in order to set operating points that minimize false positives while still allowing moderately noisy calls to be detected. A recall of 87.5% and precision of 100% with average accuracy of 96.66% suggests good generalization ability of the algorithm, and provides evidence of the validity of this approach Finally, we applied the algorithm to the available corpus, and show its potentiality to gain insights into the temporal reproductive behavior of frogs. Introduction In long term ecological studies, it is important to quantify changes that occur on biodiversity and the ecosystem as a whole. Large scale temporal and spatial studies to understand the natural and anthropogenic induced population dynamics are demanded by the scientific community. In addition, recent anuran population declines around the world have motivated studies to gain an understanding of the phenomenon [1].

Learning a policy using only observational data is challenging because the distribution of states it induces at execution time may differ from the distribution observed during training. We propose to train a policy by unrolling a learned model of the environment dynamics over multiple time steps while explicitly penalizing two costs: the original cost the policy seeks to optimize, and an uncertainty cost which represents its divergence from the states it is trained on. We measure this second cost by using the uncertainty of the dynamics model about its own predictions, using recent ideas from uncertainty estimation for deep networks. We evaluate our approach using a large-scale observational dataset of driving behavior recorded from traffic cameras, and show that we are able to learn effective driving policies from purely observational data, with no environment interaction.

When the Apollo 11 spacecraft was orbiting the Moon prior to the first lunar landing, Nasa officials told the astronauts on board to look out for the'lovely girl with a big rabbit'. They were jokingly referring to a story from Chinese mythology in which the goddess Chang'e escapes Earth to live on the Moon with her pet, Jade Rabbit. This week, almost 50 years on from that'giant leap for mankind', the legend of Chang'e resurfaced -- and this time the joke is on the Americans as China announced it had became the first nation to land a spacecraft on the'dark side of the moon'. The robotic probe was named Chang'e 4, a product of China's £3.9 billion a year space exploration project. This week, almost 50 years on from that'giant leap for mankind', the legend of Chang'e resurfaced -- and this time the joke is on the Americans as China announced it had became the first nation to land a spacecraft on the'dark side of the moon' If ever there was a metaphor for the Communist super-power's obsessive secrecy and soaring global ambition, then this audacious secret mission provides it.

The South China Sea is host to a number of countries vying for control in the area. Attempting to develop new tactics and technologies to swing the balance in its favor, China may have found its key advantage – artificial intelligence (AI). Described as an "enabling" technology, in the same way as the combustion engine or electricity, applications range from deep-sea exploration and international investment, to cybersecurity and combat operations. Chinese scientists are currently developing plans for the first-ever AI-run colony on Earth. Designed for unmanned submarine science and defense operations, the project started at the Chinese Academy of Sciences following a visit from President Xi Jinping in April to the deep-sea research institute in Sanya, Hainan province.

Mia Dand is the CEO of Lighthouse3.com, Mia is an experienced marketing leader who helps F5000 companies innovate at scale with digital and emerging technologies. She has built and led new emerging technology programs for global brands including Google, Symantec, HP, eBay and others. Mia is a strong champion for diversity & inclusion in tech.