### Probability and Statistics explained in the context of deep learning

This article is intended for beginners in deep learning who wish to gain knowledge about probability and statistics and also as a reference for practitioners. In my previous article, I wrote about the concepts of linear algebra for deep learning in a top down approach ( link for the article) (If you do not have enough idea about linear algebra, please read that first).The same top down approach is used here.Providing the description of use cases first and then the concepts. All the example code uses python and numpy.Formulas are provided as images for reuse. Probability is the science of quantifying uncertain things.Most of machine learning and deep learning systems utilize a lot of data to learn about patterns in the data.Whenever data is utilized in a system rather than sole logic, uncertainty grows up and whenever uncertainty grows up, probability becomes relevant. By introducing probability to a deep learning system, we introduce common sense to the system.Otherwise the system would be very brittle and will not be useful.In deep learning, several models like bayesian models, probabilistic graphical models, hidden markov models are used.They depend entirely on probability concepts.

### Evaluating WordNet Features in Text Classification Models

Incorporating semantic features from the WordNet lexical database is among one of the many approaches that have been tried to improve the predictive performance of text classification models. The intuition behind this is that keywords in the training set alone may not be extensive enough to enable generation of a universal model for a category, but if we incorporate the word relationships in WordNet, a more accurate model may be possible. Other researchers have previously evaluated the effectiveness of incorporating WordNet synonyms, hypernyms, and hyponyms into text classification models. Generally, they have found that improvements in accuracy using features derived from these relationships are dependent upon the nature of the text corpora from which the document collections are extracted. In this paper, we not only reconsider the role of WordNet synonyms, hypernyms, and hyponyms in text classification models, we also consider the role of WordNet meronyms and holonyms. Incorporating these WordNet relationships into a Coordinate Matching classifier, a Naive Bayes classifier, and a Support Vector Machine classifier, we evaluate our approach on six document collections extracted from the Reuters-21578, USENET, and Digi-Trad text corpora. Experimental results show that none of the WordNet relationships were effective at increasing the accuracy of the Naive Bayes classifier. Synonyms, hypernyms, and holonyms were effective at increasing the accuracy of the Coordinate Matching classifier, and hypernyms were effective at increasing the accuracy of the SVM classifier.

### A Generalization of the Chow-Liu Algorithm and its Application to Statistical Learning

We extend the Chow-Liu algorithm for general random variables while the previous versions only considered finite cases. In particular, this paper applies the generalization to Suzuki's learning algorithm that generates from data forests rather than trees based on the minimum description length by balancing the fitness of the data to the forest and the simplicity of the forest. As a result, we successfully obtain an algorithm when both of the Gaussian and finite random variables are present.

### Gaussian-binary Restricted Boltzmann Machines on Modeling Natural Image Statistics

We present a theoretical analysis of Gaussian-binary restricted Boltzmann machines (GRBMs) from the perspective of density models. The key aspect of this analysis is to show that GRBMs can be formulated as a constrained mixture of Gaussians, which gives a much better insight into the model's capabilities and limitations. We show that GRBMs are capable of learning meaningful features both in a two-dimensional blind source separation task and in modeling natural images. Further, we show that reported difficulties in training GRBMs are due to the failure of the training algorithm rather than the model itself. Based on our analysis we are able to propose several training recipes, which allowed successful and fast training in our experiments. Finally, we discuss the relationship of GRBMs to several modifications that have been proposed to improve the model.

### A PAC-Bayesian Margin Bound for Linear Classifiers: Why SVMs work

We present a bound on the generalisation error of linear classifiers in terms of a refined margin quantity on the training set. The result is obtained in a PAC-Bayesian framework and is based on geometrical arguments in the space of linear classifiers. The new bound constitutes an exponential improvement of the so far tightest margin bound by Shawe-Taylor et al. [8] and scales logarithmically in the inverse margin. Even in the case of less training examples than input dimensions sufficiently large margins lead to nontrivial bound values and - for maximum margins - to a vanishing complexity term.Furthermore, the classical margin is too coarse a measure for the essential quantity that controls the generalisation error: the volume ratio between the whole hypothesis space and the subset of consistent hypotheses. The practical relevance of the result lies in the fact that the well-known support vector machine is optimal w.r.t. the new bound only if the feature vectors are all of the same length. As a consequence we recommend to use SVMs on normalised feature vectors only - a recommendation that is well supported by our numerical experiments on two benchmark data sets. 1 Introduction Linear classifiers are exceedingly popular in the machine learning community due to their straightforward applicability and high flexibility which has recently been boosted by the so-called kernel methods [13]. A natural and popular framework for the theoretical analysis of classifiers is the PAC (probably approximately correct) framework[11] which is closely related to Vapnik's work on the generalisation error [12]. For binary classifiers it turned out that the growth function is an appropriate measureof "complexity" and can tightly be upper bounded by the VC (Vapnik-Chervonenkis) dimension [14].