A number of classification problems need to deal with data imbalance between classes. Often it is desired to have a high recall on the minority class while maintaining a high precision on the majority class. In this paper, we review a number of resampling techniques proposed in literature to handle unbalanced datasets and study their effect on classification performance.

While the Matrix Generalized Inverse Gaussian ($\mathcal{MGIG}$) distribution arises naturally in some settings as a distribution over symmetric positive semi-definite matrices, certain key properties of the distribution and effective ways of sampling from the distribution have not been carefully studied. In this paper, we show that the $\mathcal{MGIG}$ is unimodal, and the mode can be obtained by solving an Algebraic Riccati Equation (ARE) equation [7]. Based on the property, we propose an importance sampling method for the $\mathcal{MGIG}$ where the mode of the proposal distribution matches that of the target. The proposed sampling method is more efficient than existing approaches [32, 33], which use proposal distributions that may have the mode far from the $\mathcal{MGIG}$'s mode. Further, we illustrate that the the posterior distribution in latent factor models, such as probabilistic matrix factorization (PMF) [25], when marginalized over one latent factor has the $\mathcal{MGIG}$ distribution. The characterization leads to a novel Collapsed Monte Carlo (CMC) inference algorithm for such latent factor models. We illustrate that CMC has a lower log loss or perplexity than MCMC, and needs fewer samples.

Complex behaviour in many systems arises from the stochastic interactions of spatially distributed particles or agents. Stochastic reaction-diffusion processes are widely used to model such behaviour in disciplines ranging from biology to the social sciences, yet they are notoriously difficult to simulate and calibrate to observational data. Here we use ideas from statistical physics and machine learning to provide a solution to the inverse problem of learning a stochastic reactiondiffusion process from data. Our solution relies on a nontrivial connection between stochastic reaction-diffusion processes and spatiotemporal Cox processes, a well-studied class of models from computational statistics. This connection leads to an efficient and flexible algorithm for parameter inference and model selection. Our approach shows excellent accuracy on numeric and real data examples from systems biology and epidemiology. Our work provides both insights into spatiotemporal stochastic systems, and a practical solution to a longstanding problem in computational modelling. Many complex behaviours in several disciplines originate from a common mechanism: the dynamics of locally interacting, spatially distributed agents. Examples arise at all spatial scales and in a wide range of scientific fields, from microscopic interactions of low-abundance molecules within cells, to ecological and epidemic phenomena at the continental scale. Frequently, stochasticity and spatial heterogeneity play a crucial role in determining the process dynamics and the emergence of collective behaviour [1]-[8]. Stochastic reaction-diffusion processes (SRDPs) constitute a convenient mathematical framework to model such systems. SRDPs were originally introduced in statistical physics [10, 11] to describe the collective behaviour of populations of point-wise agents performing Brownian diffusion in space and stochastically interacting with other, nearby agents according to predefined rules. The flexibility afforded by the local interaction rules has led to a wide application of SRDPs in many different scientific disciplines where complex spatiotemporal behaviours arise, from molecular biology [4, 9, 12], to ecology [13], to the social sciences [14]. Despite their popularity, SRDPs pose considerable challenges, as analytical computations are only possible for a handful of systems [8].

Neuroscience is experiencing a data revolution in which many hundreds or thousands of neurons are recorded simultaneously. Currently, there is little consensus on how such data should be analyzed. Here we introduce LFADS (Latent Factor Analysis via Dynamical Systems), a method to infer latent dynamics from simultaneously recorded, single-trial, high-dimensional neural spiking data. LFADS is a sequential model based on a variational auto-encoder. By making a dynamical systems hypothesis regarding the generation of the observed data, LFADS reduces observed spiking to a set of low-dimensional temporal factors, per-trial initial conditions, and inferred inputs. We compare LFADS to existing methods on synthetic data and show that it significantly out-performs them in inferring neural firing rates and latent dynamics.

The construction of efficient and effective decision trees remains a key topic in machine learning because of their simplicity and flexibility. A lot of heuristic algorithms have been proposed to construct near-optimal decision trees. ID3, C4.5 and CART are classical decision tree algorithms and the split criteria they used are Shannon entropy, Gain Ratio and Gini index respectively. All the split criteria seem to be independent, actually, they can be unified in a Tsallis entropy framework. Tsallis entropy is a generalization of Shannon entropy and provides a new approach to enhance decision trees' performance with an adjustable parameter $q$. In this paper, a Tsallis Entropy Criterion (TEC) algorithm is proposed to unify Shannon entropy, Gain Ratio and Gini index, which generalizes the split criteria of decision trees. More importantly, we reveal the relations between Tsallis entropy with different $q$ and other split criteria. Experimental results on UCI data sets indicate that the TEC algorithm achieves statistically significant improvement over the classical algorithms.

Ligand-based virtual screening is based on the assumption that similar compounds have similar biological activity [Willett, 2009]. Compound similarity can be assessed in many ways, including comparisons of molecular "fingerprints" that encode structural features or molecular properties [Todeschini and Consonni, 2009] and measurements of shape, chemical, and/or electrostatic similarity in three dimensions [Hawkins et al., 2007; Muchmore et al., 2006; Ballester and Richards, 2007]. Three-dimensional approaches such as rapid overlay of chemical structures (ROCS) [Hawkins et al., 2007] are especially interesting because of their potential to identify molecules that are similar from the point of view of a target protein but dissimilar in underlying chemical structure ("scaffold hopping"; [Böhm et al., 2004]). ROCS represents atoms as three-dimensional Gaussian functions [Grant and Pickup, 1995; Grant et al., 1996] and calculates similarity as a function of volume overlaps between alignments of pre-generated molecular conformers. Chemical ("color") similarity is measured by overlaps between dummy atoms marking interesting chemical functionalities: hydrogen bond donors and acceptors, charged functional groups, rings, and hydrophobic groups.

Quantum-enhanced metrology aims to estimate an unknown parameter such that the precision scales better than the shot-noise bound. Single-shot adaptive quantum-enhanced metrology (AQEM) is a promising approach that uses feedback to tweak the quantum process according to previous measurement outcomes. Techniques and formalism for the adaptive case are quite different from the usual non-adaptive quantum metrology approach due to the causal relationship between measurements and outcomes. We construct a formal framework for AQEM by modeling the procedure as a decision-making process, and we derive the imprecision and the Cram\'{e}r-Rao lower bound with explicit dependence on the feedback policy. We also explain the reinforcement learning approach for generating quantum control policies, which is adopted due to the optimal policy being non-trivial to devise. Applying a learning algorithm based on differential evolution enables us to attain imprecision for adaptive interferometric phase estimation, which turns out to be SQL when non-entangled particles are used in the scheme.

Stephanie Hay is the head of content strategy at Capital One and led the design team that created Capital One's Amazon Alexa skill earlier this year. People say them every day -- after the waiter delivers food, when finishing a customer service call or before launching a rocket into space. These two words are just fine in the context of real life, human-to-human interactions. They're also covered as a feedback loop in traditional UI design, where we can create a button that says "Done" or "Save" and know exactly to which touch point people are referring when they tap it. In human-to-robot interactions, however, that's where things get tricky.

In the current issue of Science, Stanford researchers propose an accurate way to identify poverty in areas previously void of valuable survey information, says the news statement. "We have a limited number of surveys conducted in scattered villages across the African continent, but otherwise we have very little local-level information on poverty," said study coauthor Marshall Burke, an assistant professor of Earth system science at Stanford and a fellow at the Center on Food Security and the Environment. "At the same time, we collect all sorts of other data in these areas – like satellite imagery – constantly." According to Stanford, the researchers sought to understand whether high-resolution satellite imagery – an unconventional but readily available data source – could inform estimates of where impoverished people live. "The difficulty was that while standard machine learning approaches work best when they can access vast amounts of data, in this case there was little data on poverty to start with," the release says.

XGBoost is a popular implementation of Gradient Boosting because of its speed and performance. Internally, XGBoost models represent all problems as a regression predictive modeling problem that only takes numerical values as input. If your data is in a different form, it must be prepared into the expected format. In this post you will discover how to prepare your data for using with gradient boosting with the XGBoost library in Python. Data Preparation for Gradient Boosting with XGBoost in Python Photo by Ed Dunens, some rights reserved.