Determining the number of clusters when performing unsupervised clustering is a tricky problem. Many data sets don't exhibit well separated clusters, and two human beings asked to visually tell the number of clusters by looking at a chart, are likely to provide two different answers. Sometimes clusters overlap with each other, and large clusters contain sub-clusters, making a decision not easy. For instance, how many clusters do you see in the picture below? What is the optimum number of clusters?

Employee turn-over (also known as "employee churn") is a costly problem for companies. The true cost of replacing an employee can often be quite large. A study by the Center for American Progress found that companies typically pay about one-fifth of an employee's salary to replace that employee, and the cost can significantly increase if executives or highest-paid employees are to be replaced. In other words, the cost of replacing employees for most employers remains significant. This is due to the amount of time spent to interview and find a replacement, sign-on bonuses, and the loss of productivity for several months while the new employee gets accustomed to the new role. Understanding why and when employees are most likely to leave can lead to actions to improve employee retention as well as possibly planning new hiring in advance.

H2O WORLD SAN FRANCISCO – H2O.ai, the open source leader in AI and ML, today announced new and innovative capabilities for its data science and machine learning platforms, H2O, AutoML and H2O Driverless AI, to address the critical scalability and performance needs of all organizations. As part of these new capabilities, and to further the company's mission to democratize AI, H2O.ai has added several new algorithms that address common use cases that customers need today. In addition, H2O Driverless AI is a winner of InfoWorld's 2019 Technology of the Year for the second year in a row. The award honors and recognizes the best in software development, cloud computing, big data analytics, and machine learning tools. This year's judging panel recognized H2O Driverless AI for outpacing all other vendors with "automated simplicity" of its algorithms that do the heavy lifting of feature engineering, model selection, training and optimization – enabling even non-AI experts to uncover hidden patterns using both supervised and unsupervised machine learning.

Last year, we announced Snap ML, a python-based machine learning framework that is designed to be a high-performance machine learning software framework. Snap ML is bundled as part of the WML Community Edition or WML CE (aka PowerAI) software distribution that is available for free on Power systems. The first release of Snap ML enabled GPU-acceleration of generalized linear models (GLMs) and also enabled scaling these models to multiple GPUs and multiple servers. GLMs are popular machine learning algorithms, which include logistic regression, linear regression, ridge and lasso regression, and support vector machines (SVMs). Our previous blog showed that Logistic Regression using Snap ML is 46 times faster than other methods, which rely on CPUs alone.

The course "Machine Learning Basics: Building a Regression model in R" teaches you all the steps of creating a Linear Regression model, which is the most popular Machine Learning model, to solve business problems. Machine Learning is a field of computer science which gives the computer the ability to learn without being explicitly programmed. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention. What is the Linear regression technique of Machine learning? Linear Regression is a simple machine learning model for regression problems, i.e., when the target variable is a real value.

We introduce the isoperimetric loss as a regularization criterion for learning the map from a visual representation to a semantic embedding, to be used to transfer knowledge to unknown classes in a zero-shot learning setting. We use a pre-trained deep neural network model as a visual representation of image data, a Word2Vec embedding of class labels, and linear maps between the visual and semantic embedding spaces. However, the spaces themselves are not linear, and we postulate the sample embedding to be populated by noisy samples near otherwise smooth manifolds. We exploit the graph structure defined by the sample points to regularize the estimates of the manifolds by inferring the graph connectivity using a generalization of the isoperimetric inequalities from Riemannian geometry to graphs. Surprisingly, this regularization alone, paired with the simplest baseline model, outperforms the state-of-the-art among fully automated methods in zero-shot learning benchmarks such as AwA and CUB. This improvement is achieved solely by learning the structure of the underlying spaces by imposing regularity.

In the present scenario of domestic flights in USA, there have been numerous instances of flight delays and cancellations. In the United States, the American Airlines, Inc. have been one of the most entrusted and the world's largest airline in terms of number of destinations served. But when it comes to domestic flights, AA has not lived up to the expectations in terms of punctuality or on-time performance. Flight Delays also result in airline companies operating commercial flights to incur huge losses. So, they are trying their best to prevent or avoid Flight Delays and Cancellations by taking certain measures. This study aims at analyzing flight information of US domestic flights operated by American Airlines, covering top 5 busiest airports of US and predicting possible arrival delay of the flight using Data Mining and Machine Learning Approaches. The Gradient Boosting Classifier Model is deployed by training and hyper-parameter tuning it, achieving a maximum accuracy of 85.73%. Such an Intelligent System is very essential in foretelling flights'on-time performance.

Modeling item complementariness and user preferences from purchase data is essential for learning good representations of products and customers, which empowers the modern personalized recommender system for Walmart's e-commerce platform. The intrinsic complementary relationship among products captures the buy-also-buy patterns and provides great sources for recommendations. Product complementary patterns, though often reflected by population purchase behaviors, are not separable from customer-specific bias in purchase data. We propose a unified model with Bayesian network structure that takes account of both factors. In the meantime, we merge the contextual knowledge of both products and customers into their representations. We also use the dual product embeddings to capture the intrinsic properties of complementariness, such as asymmetry. The separating hyperplane theory sheds light on the geometric interpretation of using the additional embedding. We conduct extensive evaluations on our model before final production, and propose a novel ranking criterion based on product and customer embeddings. Our method compares favorably to existing approaches in various offline and online testings, and case studies demonstrate the advantage and usefulness of the dual product embeddings as well as the user embeddings.

The dying ReLU refers to the problem when ReLU neurons become inactive and only output 0 for any input. There are many empirical and heuristic explanations on why ReLU neurons die. However, little is known about its theoretical analysis. In this paper, we rigorously prove that a deep ReLU network will eventually die in probability as the depth goes to infinite. Several methods have been proposed to alleviate the dying ReLU. Perhaps, one of the simplest treatments is to modify the initialization procedure. One common way of initializing weights and biases uses symmetric probability distributions, which suffers from the dying ReLU. We thus propose a new initialization procedure, namely, a randomized asymmetric initialization. We prove that the new initialization can effectively prevent the dying ReLU. All parameters required for the new initialization are theoretically designed. Numerical examples are provided to demonstrate the effectiveness of the new initialization procedure.

In the monitoring of a complex electric grid, it is of paramount importance to provide operators with early warnings of anomalies detected on the network, along with a precise classification and diagnosis of the specific fault type. In this paper, we propose a novel multi-stage early warning system prototype for electric grid fault detection, classification, subgroup discovery, and visualization. In the first stage, a computationally efficient anomaly detection method based on quartiles detects the presence of a fault in real time. In the second stage, the fault is classified into one of nine pre-defined disaster scenarios. The time series data are first mapped to highly discriminative features by applying dimensionality reduction based on temporal autocorrelation. The features are then mapped through one of three classification techniques: support vector machine, random forest, and artificial neural network. Finally in the third stage, intra-class clustering based on dynamic time warping is used to characterize the fault with further granularity. Results on the Bonneville Power Administration electric grid data show that i) the proposed anomaly detector is both fast and accurate; ii) dimensionality reduction leads to dramatic improvement in classification accuracy and speed; iii) the random forest method offers the most accurate, consistent, and robust fault classification; and iv) time series within a given class naturally separate into five distinct clusters which correspond closely to the geographical distribution of electric grid buses.