Deep learning models are often successfully trained using gradient descent, despite the worst case hardness of the underlying non-convex optimization problem. The key question is then under what conditions can one prove that optimization will succeed. Here we provide a strong result of this kind. We consider a neural net with one hidden layer and a convolutional structure with no overlap and a ReLU activation function. For this architecture we show that learning is NP-complete in the general case, but that when the input distribution is Gaussian, gradient descent converges to the global optimum in polynomial time. To the best of our knowledge, this is the first global optimality guarantee of gradient descent on a convolutional neural network with ReLU activations.

If you have ever competed in a Kaggle competition, you are probably familiar with the use of combining different predictive models for improved accuracy which will creep your score up in the leader board. While it is widely used, there are only a few resources that I am aware of where a clear description is available (One that I know of is here, and there is also a caret package extension for it). Therefore, I will try to workout a simple example here to illustrate how different models can be combined. The example I have chosen is the House Prices competition from Kaggle. This is a regression problem and given lots of features about houses, one is expected to predict their prices on a test set.

The Microsoft Data Science Virtual machine (VM) is a custom Azure VM based on Windows Server 2012 with several popular tools for data science modeling/development like: * SQL Server 2016 Developer Edition * Microsoft R server Developer Edition * Anaconda Python with Juypter notebooks * Visual Studio 2015 Community edition with language and Azure tools and * ML and Deep Learning tools like xgboost, CNTK, mxnet More information on how to use the VM can be found on the [documentation page](http://aka.ms/dsvmdoc). If are wondering about things you can do with the DSVM read this [How-To Guide to the Data Science Virtual Machine](http://aka.ms/dsvmtenthings). Here is a list of key software on the Data Science Virtual Machine and comparison between the Windows and Linux editions of the product.

We've traditionally seen machine learning interview questions pop up in several categories. The first really has to do with the algorithms and theory behind machine learning. You'll have to show an understanding of how algorithms compare with one another and how to measure their efficacy and accuracy in the right way. The second category has to do with your programming skills and your ability to execute on top of those algorithms and the theory. The third has to do with your general interest in machine learning: you'll be asked about what's going on in the industry and how you keep up with the latest machine learning trends. Finally, there are company or industry-specific questions that test your ability to take your general machine learning knowledge and turn it into actionable points to drive the bottom line forward. We've divided this guide to machine learning interview questions into the categories we mentioned above so that you can more easily get to the information you need when it comes to machine learning interview questions. These algorithms questions will test your grasp of the theory behind machine learning.

Age and gender play a major role in someone's identification. Automatic age and gender classification has become relevant to an increasing amount of applications, particularly since the rise of social platforms and social media. Hiding true values of these variables can cause for security issues mainly. When it comes to Image Processing, an image or a video frame is taken as the input and by processing, expected predictions will be out putted. As the processing mechanism various algorithms and techniques have been used since years.

This paper is concerned with the problem of stochastic control of gene regulatory networks (GRNs) observed indirectly through noisy measurements and with uncertainty in the intervention inputs. The partial observability of the gene states and uncertainty in the intervention process are accounted for by modeling GRNs using the partially-observed Boolean dynamical system (POBDS) signal model with noisy gene expression measurements. Obtaining the optimal infinite-horizon control strategy for this problem is not attainable in general, and we apply reinforcement learning and Gaussian process techniques to find a near-optimal solution. The POBDS is first transformed to a directly-observed Markov Decision Process in a continuous belief space, and the Gaussian process is used for modeling the cost function over the belief and intervention spaces. Reinforcement learning then is used to learn the cost function from the available gene expression data. In addition, we employ sparsification, which enables the control of large partially-observed GRNs. The performance of the resulting algorithm is studied through a comprehensive set of numerical experiments using synthetic gene expression data generated from a melanoma gene regulatory network.

Microwave-based breast cancer detection has been proposed as a complementary approach to compensate for some drawbacks of existing breast cancer detection techniques. Among the existing microwave breast cancer detection methods, machine learning-type algorithms have recently become more popular. These focus on detecting the existence of breast tumours rather than performing imaging to identify the exact tumour position. A key step of the machine learning approaches is feature extraction. One of the most widely used feature extraction method is principle component analysis (PCA). However, it can be sensitive to signal misalignment. This paper presents an empirical mode decomposition (EMD)-based feature extraction method, which is more robust to the misalignment. Experimental results involving clinical data sets combined with numerically simulated tumour responses show that combined features from EMD and PCA improve the detection performance with an ensemble selection-based classifier.

We study the problem of using i.i.d. samples from an unknown multivariate probability distribution $p$ to estimate the mutual information of $p$. This problem has recently received attention in two settings: (1) where $p$ is assumed to be Gaussian and (2) where $p$ is assumed only to lie in a large nonparametric smoothness class. Estimators proposed for the Gaussian case converge in high dimensions when the Gaussian assumption holds, but are brittle, failing dramatically when $p$ is not Gaussian. Estimators proposed for the nonparametric case fail to converge with realistic sample sizes except in very low dimensions. As a result, there is a lack of robust mutual information estimators for many realistic data. To address this, we propose estimators for mutual information when $p$ is assumed to be a nonparanormal (a.k.a., Gaussian copula) model, a semiparametric compromise between Gaussian and nonparametric extremes. Using theoretical bounds and experiments, we show these estimators strike a practical balance between robustness and scaling with dimensionality.

For many internet businesses, presenting a given list of items in an order that maximizes a certain metric of interest (e.g., click-through-rate, average engagement time etc.) is crucial. We approach the aforementioned task from a learning-to-rank perspective which reveals a new problem setup. In traditional learning-to-rank literature, it is implicitly assumed that during the training data generation one has access to the \emph{best or desired} order for the given list of items. In this work, we consider a problem setup where we do not observe the desired ranking. We present two novel solutions: the first solution is an extension of already existing listwise learning-to-rank technique--Listwise maximum likelihood estimation (ListMLE)--while the second one is a generic machine learning based framework that tackles the problem in its entire generality. We discuss several challenges associated with this generic framework, and propose a simple \emph{item-payoff} and \emph{positional-gain} model that addresses these challenges. We provide training algorithms, inference procedures, and demonstrate the effectiveness of the two approaches over traditional ListMLE on synthetic as well as on real-life setting of ranking news articles for increased dwell time.

Given a knowledge base (KB) rich in facts about common nouns or generics, such as "all trees produce oxygen" or "some animals live in forests", we consider the problem of deriving additional such facts at a high precision. While this problem has received much attention for named entity KBs such as Freebase, little emphasis has been placed on generics despite their importance for capturing general knowledge. Different from named entity KBs, generics KBs involve implicit or explicit quantification, have more complex underlying regularities, are substantially more incomplete, and violate the commonly used locally closed world assumption (LCWA). Consequently, existing completion methods struggle with this new task. We observe that external information, such as relation schemas and entity taxonomies, if used correctly, can be surprisingly powerful in addressing the challenges associated with generics. Using this insight, we propose a simple yet effective knowledge guided tensor factorization approach that achieves state-of-the-art results on two generics KBs for science, doubling their size at 74\%-86\% precision. Further, to address the paucity of facts about rare entities such as oriole (a bird), we present a novel taxonomy guided submodular active learning method to collect additional annotations that are over five times more effective in inferring further new facts than multiple active learning baselines.