We consider the task of weakly supervised one-shot detection. In this task, we attempt to perform a detection task over a set of unseen classes, when training only using weak binary labels that indicate the existence of a class instance in a given example. The model is conditioned on a single exemplar of an unseen class and a target example that may or may not contain an instance of the same class as the exemplar. A similarity map is computed by using a Siamese neural network to map the exemplar and regions of the target example to a latent representation space and then computing cosine similarity scores between representations. An attention mechanism weights different regions in the target example, and enables learning of the one-shot detection task using the weaker labels alone. The model can be applied to detection tasks from different domains, including computer vision object detection. We evaluate our attention Siamese networks on a one-shot detection task from the audio domain, where it detects audio keywords in spoken utterances. Our model considerably outperforms a baseline approach and yields a 42.6% average precision for detection across 10 unseen classes. Moreover, architectural developments from computer vision object detection models such as a region proposal network can be incorporated into the model architecture, and results show that performance is expected to improve by doing so.

The field of Multi-Agent System (MAS) is an active area of research within Artificial Intelligence, with an increasingly important impact in industrial and other real-world applications. Within a MAS, autonomous agents interact to pursue personal interests and/or to achieve common objectives. Distributed Constraint Optimization Problems (DCOPs) have emerged as one of the prominent agent architectures to govern the agents' autonomous behavior, where both algorithms and communication models are driven by the structure of the specific problem. During the last decade, several extensions to the DCOP model have enabled them to support MAS in complex, real-time, and uncertain environments. This survey aims at providing an overview of the DCOP model, giving a classification of its multiple extensions and addressing both resolution methods and applications that find a natural mapping within each class of DCOPs. The proposed classification suggests several future perspectives for DCOP extensions, and identifies challenges in the design of efficient resolution algorithms, possibly through the adaptation of strategies from different areas.

The present paper aims to demonstrate the usage of Convolutional Neural Networks as a generative model for stochastic processes, enabling researchers from a wide range of fields - such as quantitative finance and physics - to develop a general tool for forecasts and simulations without the need to identify/assume a specific system structure or estimate its parameters.

Chile's Atacama Desert makes for great stargazing. The dry air and sparse settlement are a major draw for astronomical observatories--the European Southern Observatory, the Carnegie Institution for Science, and the Llano de Chajnantor Observatory all operate multiple telescope sites on the region's mountaintops. The desert wind, however, is a problem. The air rushes around and through the enclosures that hold these massive but sensitive, precise instruments. Typically, observatories have responded with heavy mounts and robust structures that keep the mirrors steady amid the turbulence.

Didi Chuxing, the ride-sharing giant of China and likely the most valuable startup in the world, just bought a controlling stake in 99, a leading ride-sharing app in Brazil. Didi already had a minority stake in the startup, having invested $100 million over a year ago. "Globalization is a top strategic priority for Didi," Cheng Wei, founder and CEO of Didi, said in a statement. "With enhanced investments in AI capabilities and smart transportation solutions, we will continue to advance the transformation of global transportation and automotive industries through diversified international operations and partnerships." The news follows the announcement that Didi plans to expand into Mexico in 2018, intensifying its global rivalry with Uber.

Recently, linear formulations and convex optimization methods have been proposed to predict diffusion-weighted Magnetic Resonance Imaging (dMRI) data given estimates of brain connections generated using tractography algorithms. The size of the linear models comprising such methods grows with both dMRI data and connectome resolution, and can become very large when applied to modern data. In this paper, we introduce a method to encode dMRI signals and large connectomes, i.e., those that range from hundreds of thousands to millions of fascicles (bundles of neuronal axons), by using a sparse tensor decomposition. We show that this tensor decomposition accurately approximates the Linear Fascicle Evaluation (LiFE) model, one of the recently developed linear models. We provide a theoretical analysis of the accuracy of the sparse decomposed model, LiFESD, and demonstrate that it can reduce the size of the model significantly. Also, we develop algorithms to implement the optimisation solver using the tensor representation in an efficient way.

LUIS is now generally available in the Australia East, Brazil South, West US 2, South Central US, East US, East Asia, and North Europe regions, in addition to the current availability in the East US 2, West Central US, West US, West Europe, and Southeast Asia regions. General availability (GA) pricing will begin on February 1, 2018. Usage prior to February 1, 2018, will be billed at preview rates.

Worrying about Artificial Intelligence (AI) and Internet of Things (IOT) destroying human opportunity of wealth creation today is a lot like worrying about overpopulation that could occur in Iceland, once overpopulated countries start facing civil wars, apartheid and people have no other options left but to migrate, although the feasibility of both the events happening in the coming decades is relatively high, if a strong Governance Framework is not implemented globally. At the moment nine countries pose a serious threat to technological progress and human welfare in the coming 50 years 2018–2068, these nine countries are expected to account for half of the world's projected population increase: Bangladesh, Brazil, China, India, Indonesia, Nigeria, Pakistan, Uganda and the United States of America. Out of these nine, China, Brazil and the United States have a firm resolve to slow down the growth rate by adopting the best possible methods to do it. Others will have no other option but to plan a stark reduction in human population in the coming decades. The exponential population growth and seemingly drastic reduction of Earths finite resources along with the threat of war, might restrain AI from reaching a conclusion that AI cannot keep up its pace with growing human numbers, which are detrimental to AI and human existence itself. This population growth is not a direct product of increasing population but also directly proportional to improved survival rate, lower child mortality rate and rapid improvements in the field of medicine.

Latent Semantic Analysis (LSA) and Word2vec are some of the most widely used word embeddings. Despite the popularity of these techniques, the precise mechanisms by which they acquire new semantic relations between words remain unclear. In the present article we investigate whether LSA and Word2vec capacity to identify relevant semantic dimensions increases with size of corpus. One intuitive hypothesis is that the capacity to identify relevant dimensions should increase as the amount of data increases. However, if corpus size grow in topics which are not specific to the domain of interest, signal to noise ratio may weaken. Here we set to examine and distinguish these alternative hypothesis. To investigate the effect of corpus specificity and size in word-embeddings we study two ways for progressive elimination of documents: the elimination of random documents vs. the elimination of documents unrelated to a specific task. We show that Word2vec can take advantage of all the documents, obtaining its best performance when it is trained with the whole corpus. On the contrary, the specialization (removal of out-of-domain documents) of the training corpus, accompanied by a decrease of dimensionality, can increase LSA word-representation quality while speeding up the processing time. Furthermore, we show that the specialization without the decrease in LSA dimensionality can produce a strong performance reduction in specific tasks. From a cognitive-modeling point of view, we point out that LSA's word-knowledge acquisitions may not be efficiently exploiting higher-order co-occurrences and global relations, whereas Word2vec does.

It's hard to believe how fast 2017 has already gone by here at BigML. It has been a banner year with many firsts thanks to the Machine Learning freight train running on all cylinders across the global economy. Gone are the days, when we often found ourselves describing what Machine Learning is and why it matters for businesses. Instead, here we are in the closing days of 2017 exchanging ideas on new use cases Machine Learning can be applied towards with business leaders. When things happen so fast, one can sometimes find it a challenge to stop and reflect on milestones and achievements.