Machine learning (ML) offers a hypothesis-free approach to modelling complex data. We present a review of ML techniques pertinent to the study of animal behaviour. Key ML approaches are illustrated using three different case studies. ML offers a useful addition to the animal behaviourist's analytical toolbox. In many areas of animal behaviour research, improvements in our ability to collect large and detailed data sets are outstripping our ability to analyse them.

Here I offer a few off-the-beaten-path interesting problems that you won't find in textbooks, data science camps, or in college classes. These problems range from applied maths, to statistics and computer science, and are aimed at getting the novice interested in a few core subjects that most data scientists master. The problems are described in simple English and don't require math / stats / probability knowledge beyond high school level. My goal is to attract people interested in data science, but who are somewhat concerned by the depth and volume of (in my opinion) unnecessary mathematics included in many curricula. I believe that successful data science can be engineered and deployed by scientists coming from other disciplines, who do not necessarily have a deep analytical background yet are familiar with data.

LONDON--(BUSINESS WIRE)--Artificial intelligence and additive manufacturing or 3D printing are emerging technologies that have a huge potential in a variety of industries and applications. Despite both technologies being fairly new, particularly 3D printing, procurement market intelligence experts at SpendEdge state that these technologies have several applications in the supply chain for addressing procurement challenges, and will very soon become an integral part due to its improved and sophisticated functionalities. Rapid prototyping is one of the most common uses of additive manufacturing. Since designing a successful product can be very expensive and time-consuming, 3D printed prototyping makes it quite simple at the same time shortens the manufacturing cycle. The impact of AM on supply chain is massive, some of which include increased manufacturing flexibility, reduced material waste, and the ability to employ decentralized manufacturing strategies.

Google CEO Sundar Pichai was obviously excited when he spoke to developers about a blockbuster result from his machine-learning lab earlier this month. Researchers had figured out how to automate some of the work of crafting machine-learning software, something that could make it much easier to deploy the technology in new situations and industries. But the project had already gained a reputation among AI researchers for another reason: the way it illustrated the vast computing resources needed to compete at the cutting edge of machine learning. A paper from Google's researchers says they simultaneously used as many as 800 of the powerful and expensive graphics processors that have been crucial to the recent uptick in the power of machine learning (see "10 Breakthrough Technologies 2013: Deep Learning"). They told MIT Technology Review that the project had tied up hundreds of the chips for two weeks solid--making the technique too resource-intensive to be more than a research project even at Google.

Perhaps the flat delivery, the Christmas word salad and the elementary melody tipped you off to the computer-generated nature of this performance. It's from a team at the University of Toronto Computer Science Department, which has been teaching a computer to write sing-along music. Dubbed "neural karaoke," this artificial intelligence system has been fed more than 100 hours of music to learn how to create simple melodies. It was also trained to recognize images and compose related lyrics. Using an algorithm, the AI finds patterns in the data and essentially "learns" music -- including beats and chords. It learned the correlation between lyrics and music notes from around 50 hours of pop songs, says Hang Chu, one of the researchers.

Facebooks' announcement last month that it's building a brain-computer interface (BMI) that will let users type with just their minds without invasive implants is exciting as it is concerning. The prospect of being able to type with just your mind at a speed of 100 words per minute – 5 times faster than the typing speed on a phone – which is Facebook's goal, is fascinating. You can get more done with lesser effort and in shorter time, right? But how effectively will users' privacy be protected when this happens and how transparent will Facebook be about it? Like in George Orwell's 1984, is this about governments or corporations wanting to read people's mind to detect thought crime?

That's because, to paraphrase Amazon's Jeff Bezos, artificial intelligence (AI) is "not just in the first inning of a long baseball game, but at the stage where the very first batter comes up." Look around, and you will find AI everywhere--in self driving cars, Siri on your phone, online customer support, movie recommendations on Netflix, fraud detection for your credit cards, etc. To be sure, there's more to come. Featuring 30 lectures, MIT's course "introduces students to the basic knowledge representation, problem solving, and learning methods of artificial intelligence." It includes interactive demonstrations designed to "help students gain intuition about how artificial intelligence methods work under a variety of circumstances."

Belief propagation (BP) is an iterative method to perform approximate inference on arbitrary graphical models. Whether BP converges and if the solution is a unique fixed point depends on both the structure and the parametrization of the model. To understand this dependence it is interesting to find \emph{all} fixed points. In this work, we formulate a set of polynomial equations, the solutions of which correspond to BP fixed points. To solve such a nonlinear system we present the numerical polynomial-homotopy-continuation (NPHC) method. Experiments on binary Ising models and on error-correcting codes show how our method is capable of obtaining all BP fixed points. On Ising models with fixed parameters we show how the structure influences both the number of fixed points and the convergence properties. We further asses the accuracy of the marginals and weighted combinations thereof. Weighting marginals with their respective partition function increases the accuracy in all experiments. Contrary to the conjecture that uniqueness of BP fixed points implies convergence, we find graphs for which BP fails to converge, even though a unique fixed point exists. Moreover, we show that this fixed point gives a good approximation, and the NPHC method is able to obtain this fixed point.

Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate the learning of a reinforcement learning agent in an off-policy setting. In addition to selecting appropriate sequences, we also artificially construct transition sequences using information gathered from previous agent-environment interactions. These sequences, when replayed, allow value function information to trickle down to larger sections of the state/state-action space, thereby making the most of the agent's experience. We demonstrate our approach on modified versions of standard reinforcement learning tasks such as the mountain car and puddle world problems and empirically show that it enables better learning of value functions as compared to other forms of experience replay. Further, we briefly discuss some of the possible extensions to this work, as well as applications and situations where this approach could be particularly useful.