The method presented extends a given regression neural network to make its performance improve. The modification affects the learning procedure only, hence the extension may be easily omitted during evaluation without any change in prediction. It means that the modified model may be evaluated as quickly as the original one but tends to perform better. This improvement is possible because the modification gives better expressive power, provides better behaved gradients and works as a regularization. The knowledge gained by the temporarily extended neural network is contained in the parameters shared with the original neural network. The only cost is an increase in learning time.

This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back-propagation, which infers the latent factors by Langevin dynamics or gradient descent. (2) Learning back-propagation, which updates the parameters given the inferred latent factors by gradient descent. The gradient computations in both steps are powered by back-propagation, and they share most of their code in common. We show that the alternating back-propagation algorithm can learn realistic generator models of natural images, video sequences, and sounds. Moreover, it can also be used to learn from incomplete or indirect training data.

This paper presents Rudra, a parameter server based distributed computing framework tuned for training large-scale deep neural networks. Using variants of the asynchronous stochastic gradient descent algorithm we study the impact of synchronization protocol, stale gradient updates, minibatch size, learning rates, and number of learners on runtime performance and model accuracy. We introduce a new learning rate modulation strategy to counter the effect of stale gradients and propose a new synchronization protocol that can effectively bound the staleness in gradients, improve runtime performance and achieve good model accuracy. Our empirical investigation reveals a principled approach for distributed training of neural networks: the mini-batch size per learner should be reduced as more learners are added to the system to preserve the model accuracy. We validate this approach using commonly-used image classification benchmarks: CIFAR10 and ImageNet.

Smoking cigarettes is the leading cause of lung cancer, the most common cause of cancer death in the world. But nearly 20 percent of lung-cancer diagnoses are made in people who are non-smokers. That means in addition to smoking, geographic, demographic and genetic factors play a role in the devastating disease. A project from Microsoft's research labs is exploring the feasibility of using anonymized web search data to learn more about lung-cancer risk factors and provide early warning to people who are candidates for disease screening. The findings, published Thursday in JAMA Oncology, extend research that team members published last June on the feasibility of using the text of questions people ask search engines to predict diagnoses of pancreatic cancer.

Artificial intelligence software can now help cops spot new or previously unknown child sexual abuse media and prosecute offenders. The toolkit, described in a paper published in Digital Investigation, automatically detects new child sexual abuse photos and videos in online peer-to-peer networks. The new approach combines automatic filename and media analysis techniques in an intelligent filtering module, which can identify new criminal media and distinguish it from other media being shared, such as adult pornography. Spotting newly produced media online can give law enforcement agencies the fresh evidence they need to find and prosecute offenders. "Identifying new child sexual abuse media is critical because it can indicate recent or ongoing child abuse," said lead study author Claudia Peersman from Lancaster University.

A simple algorithm could explain the inner workings of human intelligence, and it could one day be encoded into artificial intelligence (AI) systems, researchers suggest. It's a mind-bending idea: that all the complex thoughts running through our heads are the product of a set of definable sums. But scientists have identified clear patterns in the brains of mice and hamsters, and if a similar phenomenon could be found in human brains, it could form the basis of such an algorithm for intelligence. "Many people have long speculated that there has to be a basic design principle from which intelligence originates and the brain evolves, like how the double helix of DNA and genetic codes are universal for every organism," says lead researcher Joe Tsien from Augusta University in Georgia. "We present evidence that the brain may operate on an amazingly simple mathematical logic."

Top Gun pitted Maverick and Goose against the Iceman and Viper. At the UK Drones Show Championships at Birmingham NEC on Sunday, it was Saggy Nun and Collision who competed to be crowned the nation's fastest pilot of an unmanned flying vehicle. It was Collision, aka 22-year-old graduate trainee Brett Collis, who took the £1,000 prize in this new event in which pale young men sporting special goggles synched with flying cameras navigated an illuminated 3D obstacle course in the dark. FPV (first person view) drone racing is rapidly becoming a lucrative business: Sky Sports recently decided to show a US race series on its Mix channel and in March a 15-year-old British boy called Luke Bannister won $250,000 (£173,900) when he triumphed at the World Drone Prix in Dubai. Wearing his call sign on the back of his T-shirt, Collis explained how he graduated to drone racing from video games.

About 20 percent of youth in the United States live with a mental health condition, according to the National Institute of Mental Health. The good news is that mental health professionals have smarter tools than ever before, with artificial intelligence-related technology coming to the forefront to help diagnose patients, often with much greater accuracy than humans. A new study published in the journal Suicide and Life-Threatening Behavior, for example, showed that machine learning is up to 93 percent accurate in identifying a suicidal person. The research, led by John Pestian, a professor at Cincinnati Children's Hospital Medical Center, involved 379 teenage patients from three area hospitals. Each patient completed standardized behavioral rating scales and participated in a semi-structured interview, answering five open-ended questions such as "Are you angry?" to stimulate conversation, according to a press release from the university.

Thank you all for the huge response to this emerging course! We are delighted to have over 2300 students in over 102 different countries and for the overwhelmingly positive and thoughtful reviews. It's such a privilege to share this important topic with everyday people in a clear and understandable way. In this introductory course, the "Backyard Data Scientist" will guide you through wilderness of Machine Learning for Data Science. Accessible to everyone, this introductory course not only explains Machine Learning, but where it fits in the "techno sphere around us", why it's important now, and how it will dramatically change our world today and for days to come.

The things that the world's highest achievers spent their entire lives discovering, that no professor or teacher will ever tell you. Because when I was in college, I was mad. I'd just read a book and everything inside was the opposite of what I was learning in all my classes. So I ran into the dean's office and said "I'm literally learning more from the books I get on Amazon for five bucks than these classes that cost thousands of dollars each!" And all she had to tell me is...they're working on it! So when I walked out that day, I swore I'd teach myself the things I should have learned in school.