Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test. Recent work on explanations for black-box models has produced tools (e.g. LIME) to show the implicit rules behind predictions, which can help us identify when models are right for the wrong reasons. However, these methods do not scale to explaining entire datasets and cannot correct the problems they reveal. We introduce a method for efficiently explaining and regularizing differentiable models by examining and selectively penalizing their input gradients, which provide a normal to the decision boundary. We apply these penalties both based on expert annotation and in an unsupervised fashion that encourages diverse models with qualitatively different decision boundaries for the same classification problem. On multiple datasets, we show our approach generates faithful explanations and models that generalize much better when conditions differ between training and test.

When I first started out learning about machine learning algorithms, it turned out to be quite a task to gain an intuition of what the algorithms are doing. Not just because it was difficult to understand all the mathematical theory and notations, but it was also plain boring. When I turned to online tutorials for answers, I could again only see equations or high level explanations without going through the detail in a majority of the cases. It was then that one of my data science colleagues introduced me to the concept of working out an algorithm in an excel sheet. And that worked wonders for me.

"The road to machine learning starts with Regression. Running a regression model is a no-brainer. Once you are finished reading this article, you'll able to build, improve, and optimize regression models on your own. Note: This article is best suited for people new to machine learning with requisite knowledge of statistics.

For the past couple of months, I have been reading and doing a lot of stuff related to machine learning and sports. I have not come up with something that has good accuracy until today. A friend suggested me to predict the projected scores since the projected scores shown on the screen during a cricket match are not very accurate. This post shows that a simple linear regression model can outperform the traditional methods and the accuracy it gives is very good. Right now, the projected scores we get on the screen during a match are not very interesting to people watching cricket.

By some estimates, 80% of an organization's data is unstructured content. This content includes web pages, call center transcripts, surveys, feedback forms, legal documents, forums, social media, and blog articles. Therefore, organizations must analyze not just transactional information but also textual content to gain insight and boost performance. A powerful way to analyze this textual content is by using text mining. Text mining typically applies machine learning techniques such as clustering, classification, association rules and predictive modeling.

This post will be about two methods that slightly modify ordinary least squares (OLS) regression – ridge regression and the lasso. Like OLS, ridge attempts to minimize residual sum of squares of predictors in a given model. However, ridge regression includes an additional'shrinkage' term – the square of the coefficient estimate – which shrinks the estimate of the coefficients towards zero. Two interesting implications of this design are the facts that when λ 0 the OLS coefficients are returned and when λ, coefficients will approach zero.

Machine Learning is a hot topic in the science world right now. By combining the powers and capabilities of both computers and humans, perplexing and unimaginable problems are being resolved as we speak. Machines nowadays can more easily handle the ginormous amount of data constantly being produced, and decipher the complexity of scientific discoveries. Researchers have begun to recognise the potential this science can have in a vast variety of fields, and it's finally being put into practice. On researching the topic, many of the techniques and algorithms will seem familiar to a lot of statisticians, engineers, programmers, mathematicians and quants.

It optimizes the number of the cluster when the clustering method is maximizing the variance among the clusters. If you are using for example K-means as clustering algorithm, your method will fail for every number of cluster you try to use! As you can see doesn't exist the right number of clusters, for this problem using the "naive" kmeans. BTW I've seen for kmeans and density based clustering algo, methods based on EM (expectation and maximizazion) and Bayesian information criterion (BIC) that are a little bit more robust than this method. Could you share the table of the points...just to play a little bit with them:)

Many real datasets contain values missing not at random (MNAR). In this scenario, investigators often perform list-wise deletion, or delete samples with any missing values, before applying causal discovery algorithms. List-wise deletion is a sound and general strategy when paired with algorithms such as FCI and RFCI, but the deletion procedure also eliminates otherwise good samples that contain only a few missing values. In this report, we show that we can more efficiently utilize the observed values with test-wise deletion while still maintaining algorithmic soundness. Here, test-wise deletion refers to the process of list-wise deleting samples only among the variables required for each conditional independence (CI) test used in constraint-based searches. Test-wise deletion therefore often saves more samples than list-wise deletion for each CI test, especially when we have a sparse underlying graph. Our theoretical results show that test-wise deletion is sound under the justifiable assumption that none of the missingness mechanisms causally affect each other in the underlying causal graph. We also find that FCI and RFCI with test-wise deletion outperform their list-wise deletion and imputation counterparts on average when MNAR holds in both synthetic and real data.

Growing interest in automatic speaker verification (ASV) systems has lead to significant quality improvement of spoofing attacks on them. Many research works confirm that despite the low equal error rate (EER) ASV systems are still vulnerable to spoofing attacks. In this work we overview different acoustic feature spaces and classifiers to determine reliable and robust countermeasures against spoofing attacks. We compared several spoofing detection systems, presented so far, on the development and evaluation datasets of the Automatic Speaker Verification Spoofing and Countermeasures (ASVspoof) Challenge 2015. Experimental results presented in this paper demonstrate that the use of magnitude and phase information combination provides a substantial input into the efficiency of the spoofing detection systems. Also waveletbased features show impressive results in terms of equal error rate. In our overview we compare spoofing performance for systems based on different classifiers. Comparison results demonstrate that the linear SVM classifier outperforms the conventional GMM approach. However, many researchers inspired by the great success of deep neural networks (DNN) approaches in the automatic speech recognition, applied DNN in the spoofing detection task and obtained quite low EER for known and unknown type of spoofing attacks.