Machine-learning provides a theoretical framework for the discovery and prioritization of bioactive compounds with desired pharmacological effects and their optimization as drug-like leads. Biological target identification and protein design are emerging areas of application. Among the many machine-learning approaches in molecular informatics, chemocentric methods have found widespread application. Their underlying logic typically follows three steps. First, there is the selection of a problem-specific set of descriptors that are believed to capture the essential properties of the molecules involved.

Then we use another map transformation, which will apply the ParseObs function to transform each Array of Double in the RDD into an Array of Cancer Observation objects. The toDF() method transforms the RDD of Array[[Cancer Observation]] into a Dataframe with the Cancer Observation class schema. Below the data is split into a training data set and a test data set, 70% of the data is used to train the model, and 30% will be used for testing. In this blog post, we showed you how to get started using Apache Spark's machine learning Logistic Regression for classification.

Predictive analytics / machine learning / artificial intelligence is a hot topic – what's it about? Using algorithms to help make better decisions has been the "next big thing in analytics" for over 25 years. It has been used in key areas such as fraud the entire time. But it's now become a full-throated mainstream business meme that features in every enterprise software keynote -- although the industry is battling with what to call it. It appears that terms like data mining, predictive analytics, and advanced analytics are considered too geeky or old for industry marketers and headline writers.

What is it that makes us worry about artificial intelligence (AI)? The White House is the latest to weigh in on the possible threats posed by clever machines in a report last week. As two of those involved write in a Comment piece on page 311, scientific and political focus on extreme future risks can distract us from problems that already exist. Part of the reason for this concentration on severe, existential threats from AI comes from misplaced attention on the possibility that such technology could develop consciousness. Recent headlines suggest that respected thinkers such as Bill Gates and Stephen Hawking are concerned about machines becoming self-aware.

In a world where the term "big data" is being thrown around like the next coming, many business leaders still struggle to understand how more information is going to help them makebetter decisions that drive their businesses forward. But the real challenge goes well beyond merely accessing more data. The key is accessing data in the right way, at the right time, and in the right format to generate beneficial insights.

Lee tells Faber for him, "a glimpse into the future," in Silicon Valley is a "glimpse into the present."

Strategic messaging that precedes human-robot interaction can help build the trust needed for effective human-robot communication and positive interaction outcomes, according to a study published in Cyberpsychology, Behavior, and Social Networking. The article entitled "Advancing the Strategic Messages Affecting Robot Trust Effect: The Dynamic of User- and Robot-Generated Content on Human-Robot Trust and Interaction Outcomes" examines the impact of Strategic Messages Affecting Robot Trust (SMART). The researchers conducted two experiments in which they studied the effects of either user-generated information or robot-generated content delivered in the pre-interaction stage on human-robot trust and interaction outcomes. "As human robot interactions become more prevalent in both our personal and professional lives, it becomes increasingly more important that we understand how to work together most effectively," says Editor-in-Chief Brenda K. Wiederhold, PhD, MBA, BCB, BCN, Interactive Media Institute, San Diego, California and Virtual Reality Medical Institute, Brussels, Belgium. "Drawing on lessons learned from previous animal-human interaction training prior to our engagement may serve to create improved trust and communications."

Those results were pretty close to human performance but still short. That previous best is no longer valid as that same team has made history in speech recognition. In the same test, Microsoft's speech recognition system managed a 5.9% WER. When the team compared those results with human transcriptionists, they were identical, making the speech recognition software as accurate as human beings when it comes to writing/reciting words spoken to them. Geoffrey Zweig, who manages the Speech & Dialog research group, was happy to finally make this breakthrough.

Professor Stephen Hawking has warned that the creation of powerful artificial intelligence will be "either the best, or the worst thing, ever to happen to humanity", and praised the creation of an academic institute dedicated to researching the future of intelligence as "crucial to the future of our civilisation and our species". Hawking was speaking at the opening of the Leverhulme Centre for the Future of Intelligence (LCFI) at Cambridge University, a multi-disciplinary institute that will attempt to tackle some of the open-ended questions raised by the rapid pace of development in AI research. "We spend a great deal of time studying history," Hawking said, "which, let's face it, is mostly the history of stupidity. So it's a welcome change that people are studying instead the future of intelligence." While the world-renowned physicist has often been cautious about AI, raising the risk that humanity could be the architect of its own destruction if it creates a superintelligence with a will of its own, he was also quick to highlight the positives that AI research can bring.

Hidden Decision Trees is a statistical and data mining methodology (just like logistic regression, SVM, neural networks or decision trees) to handle problems with large amounts of data, non-linearities and strongly correlated dependent variables. The technique is easy to implement in any programming language. It is more robust than decision trees or logistic regression, and help detect natural final nodes. Implementations typically rely heavily on large, granular hash tables. No decision tree is actually built (thus the name hidden decision trees), but the final output of an hidden decision tree procedure consists of a few hundred nodes from multiple non-overlapping small decision trees.