Completely random measures (CRM) represent the key building block of a wide variety of popular stochastic models and play a pivotal role in modern Bayesian Nonparametrics. A popular representation of CRMs as a random series with decreasing jumps is due to Ferguson and Klass (1972). This can immediately be turned into an algorithm for sampling realizations of CRMs or more elaborate models involving transformed CRMs. However, concrete implementation requires to truncate the random series at some threshold resulting in an approximation error. The goal of this paper is to quantify the quality of the approximation by a moment-matching criterion, which consists in evaluating a measure of discrepancy between actual moments and moments based on the simulation output. Seen as a function of the truncation level, the methodology can be used to determine the truncation level needed to reach a certain level of precision. The resulting moment-matching \FK algorithm is then implemented and illustrated on several popular Bayesian nonparametric models.

We address an important problem in sequence-to-sequence (Seq2Seq) learning referred to as copying, in which certain segments in the input sequence are selectively replicated in the output sequence. A similar phenomenon is observable in human language communication. For example, humans tend to repeat entity names or even long phrases in conversation. The challenge with regard to copying in Seq2Seq is that new machinery is needed to decide when to perform the operation. In this paper, we incorporate copying into neural network-based Seq2Seq learning and propose a new model called CopyNet with encoder-decoder structure. CopyNet can nicely integrate the regular way of word generation in the decoder with the new copying mechanism which can choose sub-sequences in the input sequence and put them at proper places in the output sequence. Our empirical study on both synthetic data sets and real world data sets demonstrates the efficacy of CopyNet. For example, CopyNet can outperform regular RNN-based model with remarkable margins on text summarization tasks.

This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-based games. Termed a deep reinforcement relevance network (DRRN), the architecture represents action and state spaces with separate embedding vectors, which are combined with an interaction function to approximate the Q-function in reinforcement learning. We evaluate the DRRN on two popular text games, showing superior performance over other deep Q-learning architectures. Experiments with paraphrased action descriptions show that the model is extracting meaning rather than simply memorizing strings of text.

Footage of Bryde's whales feeding has been caught on camera. It was filmed with the use of a drone in research that paves the way for further studies in marine animal behaviour. Dr Barbara Bollard-Breen a senior lecturer at Auckland University of Technology, spoke to BBC News about the importance of the footage.

A private company is aiming to break into the developing asteroid mining business with a concept that could turn the minor planetary objects into rudimentary spacefaring vessels. The Mountain View, Calif.-based Made In Space, Inc., responsible for the first 3D printer to function in zero gravity conditions, will use its additive manufacturing expertise and backing from NASA to continue work on its Project Reconstituting Asteroids into Mechanical Automata (RAMA). That initiative "turns asteroids into basic spacecraft capable of moving themselves to useful locations in space," according to a blog post by Made In Space co-founder and chief technology officer Jason Dunn. NASA itself is already invested in the further study of the near-Earth objects (NEOs), and even aims to move a portion of an asteroid into Earth's orbit in the near future. And with the once-theoretical asteroid mining business now on its way to becoming an international industry, utilizing the cosmic bodies for the transport and harvesting of resources is now a practical interest.

What is the goal of UCIPT's Twitter sentiment model? The goal of the Twitter sentiment model is to predict the sentiment (positive, neutral, or negative) of a given tweet accurately. However, it is only a part of the big picture that our group has in mind. By developing a model that can predict sentiments of tweets accurately, we intend to automate the entire process of labeling an incoming stream of tweets. Through such automation, we hope to predict meaningful things such as students' stress level and GPA by analyzing a vast amount of data available on Twitter. How do you use a neural network to improve the accuracy of your predictions?

There was no single moment that everything changed for Steve Wozniak. Instead, it was years of creativity and work that led to his development of the Apple I and the Apple II computers. "I look back now and wonder how did I think of doing things that no one thought of back then?" Wozniak said, speaking at an Alltech conference. Wozniak, co-founder of Apple Computer Inc. and chief scientist at Primary Data, received the Alltech Humanitarian Award at a conference in Lexington, Ky. Watching Wozniak talk is like seeing a brilliant orator at work, as he talks about numerous subjects at a lightning fast speed and gives insightful commentary on each topic before the listener can sometimes even process what has been said on the previous subject. Despite his whirlwind mind, or perhaps because of it, Wozniak is a fascinating speaker and at the conference, he touched upon everything from AI to VR and many things in between.

Google DeepMind has poured cold water on rumours its AlphaGo Artificial Intelligence Go-playing program will face off against Chinese Go champion Ke Jie. "Contrary to internet rumours, we've not decided yet what to do next with #AlphaGo, once we have, there will be an official announcement here," Hassabis tweeted on Monday. The news was originally released by Yang Junan, secretary general of the International Go Federation, at a news conference for the 37th World Amateur Go Championship, on June 4. Yang said representatives had been in contact with the team behind AlphaGo and would set up a match by the end of this year. AlphaGo defeated South Korean Go grandmaster Lee Sedol 4-1 at the Google DeepMind Challenge Match held in March, sparking global interest in AI.

CrowdFlower is announcing that it has raised 10 million in Series D funding. The round was led by Microsoft, with participation from Canvas Ventures and Trinity Ventures. The San Francisco-based company has now raised a total of 38 million, according to CrunchBase. CrowdFlower launched at the TechCrunch50 conference (today's Startup Battlefield at TechCrunch Disrupt) back in 2009, billing itself "labor as a service" tool using platforms like Amazon's Mechanical Turk to help businesses tap a remote, crowdsourced workforce for mundane tasks like photo moderation. Founder and CEO Lukas Biewald (who I've known and been friendly with since college) said that the company's current focus is on a new artificial intelligence product.

Faraday Future isn't just talking a big game when it mentions plans for autonomous features in its cars. Michigan's Department of Transportation tells the Detroit News that FF not only asked about how to apply for plates that let it test self-driving cars, but has applied for three manufacturer plates since. While the company isn't confirming anything (the plates are to test "prototypes and features," it says), it's safe to say that at least one of those vehicles won't always have a human at the wheel.