We propose Deep Hierarchical Machine (DHM), a model inspired from the divide-and-conquer strategy while emphasizing representation learning ability and flexibility. A stochastic routing framework as used by recent deep neural decision/regression forests is incorporated, but we remove the need to evaluate unnecessary computation paths by utilizing a different topology and introducing a probabilistic pruning technique. We also show a specified version of DHM (DSHM) for efficiency, which inherits the sparse feature extraction process as in traditional decision tree with pixel-difference feature. To achieve sparse feature extraction, we propose to utilize sparse convolution operation in DSHM and show one possibility of introducing sparse convolution kernels by using local binary convolution layer. DHM can be applied to both classification and regression problems, and we validate it on standard image classification and face alignment tasks to show its advantages over past architectures.

Clinical text provides essential information to estimate the acuity of a patient during hospital stays in addition to structured clinical data. In this study, we explore how clinical text can complement a clinical predictive learning task. We leverage an internal medical natural language processing service to perform named entity extraction and negation detection on clinical notes and compose selected entities into a new text corpus to train document representations. We then propose a multimodal neural network to jointly train time series signals and unstructured clinical text representations to predict the in-hospital mortality risk for ICU patients. Our model outperforms the benchmark by 2% AUC.

Researchers at the University of Adelaide are creating machines capable of undertaking complex tasks, acknowledging the outcomes and improving their performance accordingly. That's according to Professor Anton van den Hengel, Director of the Australian Institute for Machine Learning (AIML), who claimed the university's technology can "compete with, and sometimes exceed, human capabilities in tasks like recognition, statistical analysis and classification". The breakthrough, according to Prof van den Hengel, has been the advent of'deep learning' technology -- a form of machine learning (itself a subset of artificial intelligence) based on the human brain's neural networks. "That's enabled machines to distil and interpret huge amounts of prior and incoming information, and particularly visual information," he said. Prof Ian Reid, a senior colleague of Prof van den Hengel's and Deputy Director of the Australian Centre for Robotic Vision, agrees.

Applying artificial intelligence to self-driving cars to smooth traffic, reduce fuel consumption, and improve air quality predictions may sound like the stuff of science fiction, but researchers at the Department of Energy's Lawrence Berkeley National Laboratory (Berkeley Lab) have launched two research projects to do just that. In collaboration with UC Berkeley, Berkeley Lab scientists are using deep reinforcement learning, a computational tool for training controllers, to make transportation more sustainable. One project uses deep reinforcement learning to train autonomous vehicles to drive in ways to simultaneously improve traffic flow and reduce energy consumption. A second uses deep learning algorithms to analyze satellite images combined with traffic information from cell phones and data already being collected by environmental sensors to improve air quality predictions. "Thirty percent of energy use in the U.S. is to transport people and goods, and this energy consumption contributes to air pollution, including approximately half of all nitrogen oxide emissions, a precursor to particular matter and ozone – and black carbon (soot) emissions," said Tom Kirchstetter, director of Berkeley Lab's Energy Analysis and Environmental Impacts Division, an adjunct professor at UC Berkeley, and a member of the research team.

Cutting Edge Deep Learning For Coders, Part 2 from fast.ai

A machine learning approach inspired by the human brain, Deep Learning is taking many industries by storm. Empowered by the latest generation of commodity computing, Deep Learning begins to derive significant value from Big Data. It has already radically improved the computer's ability to recognize speech and identify objects in images, two fundamental hallmarks of human intelligence.

On November 21, I read an interview with Yoshua Bengio in Technology Review that to a suprising degree downplayed recent successes in deep learning, emphasizing instead some other important problems in AI might require important extensions to what deep learning is currently able to do. I agreed with virtually every word and thought it was terrific that Bengio said so publicly. Instead I accidentally launched a Twitterstorm, at times illuminating, at times maddening, with some of the biggest folks in the field, including Bengio's fellow deep learning pioneer Yann LeCun and one of AI's deepest thinkers, Judea Pearl. Here's the tweet, perhaps forgotten in the storm that followed: For the record and for comparison, here's what I had said almost exactly six years earlier, on November 25, 2012, eerily similar, I stand by that -- which as far as I know (and I could be wrong) is the first place where anybody said that deep learning per se wouldn't be a panacea, and would instead need to work in a larger context to solve a certain class of problems. Bengio was pretty much saying the same thing.

Note: This Editorial is appearing in Speaking of Medicine ahead of print. The final version will appear in PLOS Medicine at the end of December. PLOS Medicine Machine Learning Special Issue Guest Editors Suchi Saria, Atul Butte, and Aziz Sheikh cut through the hyperbole with an accessible and accurate portrayal of the forefront of machine learning in clinical translation. Artificial Intelligence (AI) as a field emerged in the 1960s when practitioners across the engineering and cognitive sciences began to study how to develop computational technologies that, like people, can perform tasks such as sensing, learning, reasoning, and taking action. Early AI systems relied heavily on expert-derived rules for replicating how people would approach these tasks.

DeepMind Technologies is a British artificial intelligence company founded in September 2010, currently owned by Alphabet Inc.. The company is based in London, but has research centres in California, Canada[4], and France[5]. Acquired by Google in 2014, the company has created a neural network that learns how to play video games in a fashion similar to that of humans,[6] as well as a Neural Turing machine,[7] or a neural network that may be able to access an external memory like a conventional Turing machine, resulting in a computer that mimics the short-term memory of the human brain.[8][9] The company made headlines in 2016 after its AlphaGo program beat a human professional Go player for the first time in October 2015[10] and again when AlphaGo beat Lee Sedol, the world champion, in a five-game match, which was the subject of a documentary film.[11] A more generic program, AlphaZero, beat the most powerful programs playing go, chess and shogi (Japanese chess) after a few hours of play against itself using reinforcement learning.[12]

In 2017, a Palestinian construction worker in the West Bank settlement of Beiter Illit, Jerusalem, posted a picture of himself on Facebook in which he was leaning against a bulldozer. Shortly after, Israeli police arrested him on suspicions that he was planning an attack, because the caption of his post read "attack them." The real caption of the post was "good morning" in Arabic. But for some unknown reason, Facebook's artificial intelligence–powered translation service translated the text to "hurt them" in English or "attack them" in Hebrew. The Israeli Defense Force uses Facebook's automated translation to monitor the accounts of Palestinian users for possible threats. In this case, they trusted Facebook's AI enough not to have the post checked by an Arabic-speaking officer before making the arrest. The Palestinian worker was eventually released after the mistake came to light--but not before he underwent hours of questioning. Facebook apologized for the mistake and said that it took steps to correct it.