We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree models (HLTMs). The variables at the bottom level of an HLTM are observed binary variables that represent the presence/absence of words in a document. The variables at other levels are binary latent variables, with those at the lowest latent level representing word co-occurrence patterns and those at higher levels representing co-occurrence of patterns at the level below. Each latent variable gives a soft partition of the documents, and document clusters in the partitions are interpreted as topics. Latent variables at high levels of the hierarchy capture long-range word co-occurrence patterns and hence give thematically more general topics, while those at low levels of the hierarchy capture short-range word co-occurrence patterns and give thematically more specific topics. Unlike LDA-based topic models, HLTMs do not refer to a document generation process and use word variables instead of token variables. They use a tree structure to model the relationships between topics and words, which is conducive to the discovery of meaningful topics and topic hierarchies.

Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer, from the output layer to the hidden layers. A recently discovered method called feedback-alignment shows that the weights used for propagating the error backward don't have to be symmetric with the weights used for propagation the activation forward. In fact, random feedback weights work evenly well, because the network learns how to make the feedback useful. In this work, the feedback alignment principle is used for training hidden layers more independently from the rest of the network, and from a zero initial condition. The error is propagated through fixed random feedback connections directly from the output layer to each hidden layer. This simple method is able to achieve zero training error even in convolutional networks and very deep networks, completely without error back-propagation. The method is a step towards biologically plausible machine learning because the error signal is almost local, and no symmetric or reciprocal weights are required. Experiments show that the test performance on MNIST and CIFAR is almost as good as those obtained with back-propagation for fully connected networks. If combined with dropout, the method achieves 1.45% error on the permutation invariant MNIST task.

I have been writing these forecasts, largely with an emphasis on the data space, since the late 1990s. I do these less to proclaim my own prognostication scores (which run about 70% or so - not bad but not great) and more as an exercise to determine where I personally will be focusing on. In the last eighteen years, I have never found a year that was as filled with uncertainty as 2016 has been (2000 was perhaps the next worst, followed by 2007). These are inflection points in the economy, where trends usually break. For 2017, the political climate will have an impact in a way that is unprecedented on IT, and likely not for the good. However, this has been the season for unexpected results.

The Reinventing Energy Summit, hosted by New Scientist and Re.Work, occurred on November 25th in London, UK. Good Faith Energy president and founder, Mohammed Abdalla, was in attendance at the conference to gain insights on the future of renewable energy and new technologies. The event's goal was to together energy thought-leaders, policy experts, innovative startups, utility companies, and world-class academics, to explore the advancement of technologies impacting renewable energy. A record £15.2bn was invested in UK clean energy in 2015. Favorable incentives and subsidies have led to this enormous growth.

Tokyo-based SoftBank is one of Japan's biggest telecoms providers, with more than 63,590 employees, a solar power business, humanoid robots for home use, ride-booking services and financial technology. It recently set up a $25 billion private fund for technology investments, along with Saudi Arabia and other investors, that Son says could grow to $100 billion.

It will take time, but AI could offer oil and gas companies a new way of maintaining their competitive edge. The capabilities of artificial intelligence (AI) technology have grown in recent years. But further development is needed before AI's benefits can be fully reaped, The Wall Street Journal reported earlier this month. The Journal reported that AI is appearing in people's everyday lives. But many companies lack the data, problems that just the expense of creating an AI system, and lack of people capable of building such systems.

Abstract--Due to limited metering infrastructure, distribution grids are currently challenged by observability issues. On the other hand, smart meter data, including local voltage magnitudes and power injections, are communicated to the utility operator from grid buses with renewable generation and demand-response programs. This work employs grid data from metered buses towards inferring the underlying grid state. T o this end, a coupled formulation of the power flow problem (CPF) is put forth. Exploiting the high variability of injections at metered buses, the controllability of solar inverters, and the relative time-invariance of conventional loads, the idea is to solve the nonlinear power flow equations jointly over consecutive time instants. An intuitive and easily verifiable rule pertaining to the locations of metered and non-metered buses on the physical grid is shown to be a necessary and sufficient criterion for local observability in radial networks. T o account for noisy smart meter readings, a coupled power system state estimation (CPSSE) problem is further developed. Both CPF and CPSSE tasks are tackled via augmented semi-definite program relaxations. The observability criterion along with the CPF and CPSSE solvers are numerically corroborated using synthetic and actual solar generation and load data on the IEEE 34-bus benchmark feeder . Power flow (PF) and power system state estimation (PSSE) are central to planning, monitoring and control of electricity networks.

There are many forms of feature information present in video data. Principle among them are object identity information which is largely static across multiple video frames, and object pose and style information which continuously transforms from frame to frame. Most existing models confound these two types of representation by mapping them to a shared feature space. In this paper we propose a probabilistic approach for learning separable representations of object identity and pose information using unsupervised video data. Our approach leverages a deep generative model with a factored prior distribution that encodes properties of temporal invariances in the hidden feature set. Learning is achieved via variational inference. We present results of learning identity and pose information on a dataset of moving characters as well as a dataset of rotating 3D objects. Our experimental results demonstrate our model's success in factoring its representation, and demonstrate that the model achieves improved performance in transfer learning tasks.

A Graphical Model (GM) describes a probability distribution over a set of random variables which factorizes over the edges of a graph. It is of interest to recover the structure of GMs from random samples. The graphical structure contains valuable information on the dependencies between the random variables. In fact, the neighborhood of a random variable is the minimal set that provides us maximum information about this variable. Unsurprisingly, GM reconstruction plays an important role in various fields such as the study of gene expression [1], protein interactions [2], neuroscience [3], image processing [4], sociology [5] and even grid science [6, 7]. The origin of the GM reconstruction problem is traced back to the seminal 1968 paper by Chow and Liu [8], where the problem was posed and resolved for the special case of tree-structured GMs. In this special tree case the maximum likelihood estimator is tractable and is tantamount to finding a maximum weighted spanning-tree. However, it is also known that in the case of general graphs with cycles, maximum likelihood estimators are intractable as they require computation of the partition function of the underlying GM, with notable exceptions of the Gaussian GM, see for instance [9], and some other special cases, like planar Ising models without magnetic field [10]. 1 A lot of efforts in this field has focused on learning Ising models, which are the most general GMs over binary variables with pairwise interaction/factorization. Early attempts to learn the Ising model structure efficiently were heuristic, based on various mean-field approximations, e.g.

If a voice inquiry, Siri invokes a speech-to-text mechanism that transcribes what has been spoken to text. This is very difficult, by the way, particularly given the number of languages in which Siri works.