To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependences. For inference, we develop a hybrid of stochastic-gradient MCMC and recurrent autoencoding variational Bayes. Experimental results on a variety of real-world text corpora demonstrate that the proposed model not only outperforms state-of-the-art larger-context RNN-based language models, but also learns interpretable recurrent multilayer topics and generates diverse sentences and paragraphs that are syntactically correct and semantically coherent.

The field of machine learning has focused, primarily, on discretized sub-problems (i.e. vision, speech, natural language) of intelligence. While neuroscience tends to be observation heavy, providing few guiding theories. It is unlikely that artificial intelligence will emerge through only one of these disciplines. Instead, it is likely to be some amalgamation of their algorithmic and observational findings. As a result, there are a number of problems that should be addressed in order to select the beneficial aspects of both fields. In this article, we propose leading questions to guide the future of artificial intelligence research. There are clear computational principles on which the brain operates. The problem is finding these computational needles in a haystack of biological complexity. Biology has clear constraints but by not using it as a guide we are constraining ourselves.

We all know how XGBoost dominates in Kaggle competitions due to its performance and speed. This blog is about understanding how XGBoost works (try to explain the research paper). This blog is not about how to code/ implement XGboost or how to tune its hyperparameters. XGBoost stands for eXtreme Gradient Boosting. It explains bagging (bootstrap aggregating) and boosting (Adaptive Boosting).

Machine learning (ML) projects are one of the best ways to gain hands-on experience and improve applied machine learning skills. Machine Learning beginners and enthusiasts can take advantage of machine learning datasets available and get started on their learning journey. In this cheat sheet, we will look at the top 10 machine learning (ML) projects for beginners in 2020, along with the machine learning datasets required to gain experience of working on real-world problems. We have divided the projects based on tasks like classification, forecasting, prediction and mining. Here are the top machine learning projects you can explore in 2020.

--Operating envelope is an important concept in industrial operations. Accurate identification for operating envelope can be extremely beneficial to stakeholders as it provides a set of operational parameters that optimizes some key performance indicators (KPI) such as product quality, operational safety, equipment efficiency, environmental impact, etc. Given the importance, data-driven approaches for computing the operating envelope are gaining popularity. These approaches typically use classifiers such as support vector machines, to set the operating envelope by learning the boundary in the operational parameter spaces between the manually assigned'large KPI' and'small KPI' groups. One challenge to these approaches is that the assignment to these groups is often ad-hoc and hence arbitrary. However, a bigger challenge with these approaches is that they don't take into account two key features that are needed to operationalize operating envelopes: (i) interpretability of the envelope by the operator and (ii) implementability of the envelope from a practical standpoint. In this work, we propose a new definition for operating envelope which directly targets the expected magnitude of KPI (i.e., no need to arbitrarily bin the data instances into groups) and accounts for the interpretability and the implementability. We then propose a regularized'GA penalty' algorithm that outputs an envelope where the user can tradeoff between bias and variance. The validity of our proposed algorithm is demonstrated by two sets of simulation studies and an application to a real-world challenge in the mining processes of a flotation plant. In industrial operations, an important concept is that of the operating envelope. Conceptually, the operating envelope is a set of operational parameters, such that some KPI is optimized. In the industrial context, typical KPIs include product quality, operational safety, equipment efficiency, environmental impact, etc [1]-[4]. The operating envelope has wide application since it directly targets the business outcome and yields actionable recommendations in the operations space.

Shear stress distribution prediction in open channels is of utmost importance in hydraulic structural engineering as it directly affects the design of stable channels. In this study, at first, a series of experimental tests were conducted to assess the shear stress distribution in prismatic compound channels. The shear stress values around the whole wetted perimeter were measured in the compound channel with different floodplain widths also in different flow depths in subcritical and supercritical conditions. A set of, data mining and machine learning models including Random Forest (RF), M5P, Random Committee (RC), KStar and Additive Regression Model (AR) implemented on attained data to predict the shear stress distribution in the compound channel. Results indicated among these five models, RF method indicated the most precise results with the highest R2 value of 0.9. Finally, the most powerful data mining method which studied in this research (RF) compared with two well-known analytical models of Shiono and Knight Method (SKM) and Shannon method to acquire the proposed model functioning in predicting the shear stress distribution. The results showed that the RF model has the best prediction performance compared to SKM and Shannon models.

The optimization of multilayer neural networks typically leads to a solution with zero training error, yet the landscape can exhibit spurious local minima and the minima can be disconnected. In this paper, we shed light on this phenomenon: we show that the combination of stochastic gradient descent (SGD) and over-parameterization makes the landscape of multilayer neural networks approximately connected and thus more favorable to optimization. More specifically, we prove that SGD solutions are connected via a piecewise linear path, and the increase in loss along this path vanishes as the number of neurons grows large. This result is a consequence of the fact that the parameters found by SGD are increasingly dropout stable as the network becomes wider. We show that, if we remove part of the neurons (and suitably rescale the remaining ones), the change in loss is independent of the total number of neurons, and it depends only on how many neurons are left. Our results exhibit a mild dependence on the input dimension: they are dimension-free for two-layer networks and depend linearly on the dimension for multilayer networks. We validate our theoretical findings with numerical experiments for different architectures and classification tasks.

We present secml, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including not only test-time evasion attacks to generate adversarial examples against deep neural networks, but also training-time poisoning attacks against support vector machines and many other algorithms. These attacks enable evaluating the security of learning algorithms and of the corresponding defenses under both white-box and black-box threat models. To this end, secml provides built-in functions to compute security evaluation curves, showing how quickly classification performance decreases against increasing adversarial perturbations of the input data. secml also includes explainability methods to help understand why adversarial attacks succeed against a given model, by visualizing the most influential features and training prototypes contributing to each decision. It is distributed under the Apache License 2.0, and hosted at https://gitlab.com/secml/secml.

A representative model in integrative analysis of two high-dimensional data types is to decompose each data matrix into a low-rank common matrix generated by latent factors shared across data types, a low-rank distinctive matrix corresponding to each data type, and an additive noise matrix. Existing decomposition methods claim that their common matrices capture the common pattern of the two data types. However, their so-called common pattern only denotes the common latent factors but ignores the common information between the two coefficient matrices of these latent factors. We propose a novel method, called the common and distinctive pattern analysis, which appropriately defines the two patterns by further incorporating the common and distinctive information of the coefficient matrices. A consistent estimation approach is developed for high-dimensional settings, and shows reasonably good finite-sample performance in simulations. We illustrate the superiority of proposed method over the state-of-the-art by real-world data examples obtained from Human Connectome Project and The Cancer Genome Atlas.

In this paper, we try to uncover the second-order essence of several first-order optimization methods. For Nesterov Accelerated Gradient, we rigorously prove that the algorithm makes use of the difference between past and current gradients, thus approximates the Hessian and accelerates the training. For adaptive methods, we related Adam and Adagrad to a powerful technique in computation statistics---Natural Gradient Descent. These adaptive methods can in fact be treated as relaxations of NGD with only a slight difference lying in the square root of the denominator in the update rules. Skeptical about the effect of such difference, we design a new algorithm---AdaSqrt, which removes the square root in the denominator and scales the learning rate by sqrt(T). Surprisingly, our new algorithm is comparable to various first-order methods(such as SGD and Adam) on MNIST and even beats Adam on CIFAR-10! This phenomenon casts doubt on the convention view that the square root is crucial and training without it will lead to terrible performance. As far as we have concerned, so long as the algorithm tries to explore second or even higher information of the loss surface, then proper scaling of the learning rate alone will guarantee fast training and good generalization performance. To the best of our knowledge, this is the first paper that seriously considers the necessity of square root among all adaptive methods. We believe that our work can shed light on the importance of higher-order information and inspire the design of more powerful algorithms in the future.