Learned region sparsity has achieved state-of-the-art performance in classification tasks by exploiting and integrating a sparse set of local information into global decisions. The underlying mechanism resembles how people sample information from an image with their eye movements when making similar decisions. In this paper we incorporate the biologically plausible mechanism of Inhibition of Return into the learned region sparsity model, thereby imposing diversity on the selected regions. We investigate how these mechanisms of sparsity and diversity relate to visual attention by testing our model on three different types of visual search tasks. We report state-of-the-art results in predicting the locations of human gaze fixations, even though our model is trained only on image-level labels without object location annotations. Notably, the classification performance of the extended model remains the same as the original. This work suggests a new computational perspective on visual attention mechanisms, and shows how the inclusion of attention-based mechanisms can improve computer vision techniques.

Exemplar learning is a powerful paradigm for discovering visual similarities in an unsupervised manner. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With only a single positive sample, a great imbalance between one positive and many negatives, and unreliable relationships between most samples, training of convolutional neural networks is impaired. Given weak estimates of local distance we propose a single optimization problem to extract batches of samples with mutually consistent relations. Conflicting relations are distributed over different batches and similar samples are grouped into compact cliques. Learning exemplar similarities is framed as a sequence of clique categorization tasks. The CNN then consolidates transitivity relations within and between cliques and learns a single representation for all samples without the need for labels. The proposed unsupervised approach has shown competitive performance on detailed posture analysis and object classification.

This study introduces a novel feature selection approach CMICOT, which is a further evolution of filter methods with sequential forward selection (SFS) whose scoring functions are based on conditional mutual information (MI). We state and study a novel saddle point (max-min) optimization problem to build a scoring function that is able to identify joint interactions between several features. This method fills the gap of MIbased SFS techniques with high-order dependencies. In this high-dimensional case, the estimation of MI has prohibitively high sample complexity. We mitigate this cost using a greedy approximation and binary representatives whatmakes our technique able to be effectively used. The superiority of our approach is demonstrated by comparison with recently proposed interactionaware filtersand several interaction-agnostic state-of-the-art ones on ten publicly available benchmark datasets.

The wait is almost over for Ronda Rousey's return. Following a 412-day hiatus, the top female star in MMA history is ready to fight again. Friday's long night of fights in Las Vegas concludes with the UFC 207 main event between Rousey and bantamweight champion Amanda Nunes. Nunes hasn't defended the title since winning it from Miesha Tate at UFC 200, and she's an underdog against the longest-reigning champion in the 135-pound division's history. The main card for UFC 207 begins on pay-per-view at 10 p.m. EST, but it will be some time before Rousey and Nunes make their way to the octagon.

In recent years, AI (artificial intelligence) researchers have finally cracked problems that they've worked on for decades, from Go to human-level speech recognition. A key piece was the ability to gather and learn on mountains of data, which pulled error rates past the success line. In short, big data has transformed AI, to an almost unreasonable level. Blockchain technology could transform AI too, in its own particular ways. Some applications of blockchains to AI are mundane, like audit trails on AI models. Some appear almost unreasonable, like AI that can own itself -- AI DAOs. All of them are opportunities. This article will explore these applications. Before we discuss applications, let's first review what's different about blockchains compared to traditional big-data distributed databases like MongoDB. We can think of blockchains as "blue ocean"databases: they escape the "bloody red ocean" of sharks competing in an existing market, opting instead to be in a blue ocean of uncontested market space.

Get started with deep learning and neural networks with "Fundamentals of Deep Learning," by Nikhil Buduma. Security data science is booming--reports indicate that the security analytics market is set to reach $8 billion dollars by 2023, with a growth rate of 26%, thanks to relentless cyber attacks. If you want to stay ahead of emerging security threats in 2017, it is important to invest in the right areas. In March 2016, I wrote a piece on the 4 trends to be aware of for 2016; for my 2017 trends post, Cody Rioux from Netflix joins me, bringing his platform perspective. Our goal is to help you formulate a plan for every quarter of 2017 (i.e., 4 trends for 4 quarters).

There are a number of machine learning models to choose from. We can use Linear Regression to predict a value, Logistic Regression to classify distinct outcomes, and Neural Networks to model non-linear behaviors. When we build these models, we always use a set of historical data to help our machine learning algorithms learn what is the relationship between a set of input features to a predicted output. But even if this model can accurately predict a value from historical data, how do we know it will work as well on new data? Or more plainly, how do we evaluate whether a machine learning model is actually "good"?

Security data science is booming--reports indicate that the security analytics market is set to reach $8 billion dollars by 2023, with a growth rate of 26%, thanks to relentless cyber attacks. If you want to stay ahead of emerging security threats in 2017, it is important to invest in the right areas. In March 2016, I wrote a piece on the 4 trends to be aware of for 2016; for my 2017 trends post, Cody Rioux from Netflix joins me, bringing his platform perspective. Our goal is to help you formulate a plan for every quarter of 2017 (i.e., 4 trends for 4 quarters). For each of our trends, we provide a short rationale, why we think the time is right for investing, and how to capitalize on the investment, with pointers to specific tools and resources.

Random forest (Leo Breiman 2001a) (RF) is a non-parametric statistical method requiring no distributional assumptions on covariate relation to the response. RF is a robust, nonlinear technique that optimizes predictive accuracy by fitting an ensemble of trees to stabilize model estimates. Random survival forests (RSF) (Ishwaran and Kogalur 2007; Ishwaran et al. 2008) are an extension of Breimans RF techniques allowing efficient nonparametric analysis of time to event data. The randomForestSRC package (Ishwaran and Kogalur 2014) is a unified treatment of Breimans random forest for survival, regression and classification problems. Predictive accuracy makes RF an attractive alternative to parametric models, though complexity and interpretability of the forest hinder wider application of the method. We introduce the ggRandomForests package, tools for visually understand random forest models grown in R (R Core Team 2014) with the randomForestSRC package. The ggRandomForests package is structured to extract intermediate data objects from randomForestSRC objects and generate figures using the ggplot2 (Wickham 2009) graphics package. This document is structured as a tutorial for building random forest for survival with the randomForestSRC package and using the ggRandomForests package for investigating how the forest is constructed. We analyse the Primary Biliary Cirrhosis of the liver data from a clinical trial at the Mayo Clinic (Fleming and Harrington 1991). Our aim is to demonstrate the strength of using Random Forest methods for both prediction and information retrieval, specifically in time to event data settings.

The standard approach to supervised classification involves the minimization of a log-loss as an upper bound to the classification error. While this is a tight bound early on in the optimization, it overemphasizes the influence of incorrectly classified examples far from the decision boundary. Updating the upper bound during the optimization leads to improved classification rates while transforming the learning into a sequence of minimization problems. In addition, in the context where the classifier is part of a larger system, this modification makes it possible to link the performance of the classifier to that of the whole system, allowing the seamless introduction of external constraints.