This is the 5th article of series "Coding Deep Learning for Beginners". You will be able to find here links to all articles, agenda, and general information about an estimated release date of next articles on the bottom of the 1st article. They are also available in my open source portfolio -- MyRoadToAI, along with some mini-projects, presentations, tutorials and links. In this article, I will explain the concept of training Machine Learning algorithms with Gradient Descent. Majority of supervised algorithms are taking advantage of it -- especially all Neural Networks.

Rankings of universities and specialized academic programs have a major influence on students deciding what university to attend, faculty deciding where to work, government bodies deciding where and how to invest education and research funding, and university leaders deciding how to grow their institutions.9 There is general agreement in scientometrics that the quality of a university or a program depends on many factors, and different ranking metrics might be appropriate for different types of users. However, major points of contention emerge when it comes to agreeing on ranking methodology.20 Given the increasing impact of rankings, there is a need to better understand the actors influencing rankings and come up with a justifiable, transparent formula that encourages high-quality education and research at universities.11 We aim to contribute toward achieving this objective by focusing on ranking of the U.S. doctoral programs in computer science. We broadly group quality measures into objective (such as average research funding per faculty member) and subjective (such as peer assessment). The influential U.S. News ranking of computer science doctoral programsa is based purely on peer assessment in which computer science department chairs are asked to score other computer science programs on a scale of 1 to 5, with 1 being "marginal" and 5 being "outstanding," or enter "do not know" if not sufficiently familiar with the program. The final ranking is obtained by averaging the individual scores.

Global pairwise network alignment (GPNA) aims to find a one-to-one node mapping between two networks that identifies conserved network regions. GPNA algorithms optimize node conservation (NC) and edge conservation (EC). NC quantifies topological similarity between nodes. Graphlet-based degree vectors (GDVs) are a state-of-the-art topological NC measure. Dynamic GDVs (DGDVs) were used as a dynamic NC measure within the first-ever algorithms for GPNA of temporal networks: DynaMAGNA++ and DynaWAVE. The latter is superior for larger networks. We recently developed a different graphlet-based measure of temporal node similarity, graphlet-orbit transitions (GoTs). Here, we use GoTs instead of DGDVs as a new dynamic NC measure within DynaWAVE, resulting in a new approach, GoT-WAVE. On synthetic networks, GoT-WAVE improves DynaWAVE's accuracy by 25% and speed by 64%. On real networks, when optimizing only dynamic NC, each method is superior ~50% of the time. While DynaWAVE benefits more from also optimizing dynamic EC, only GoT-WAVE can support directed edges. Hence, GoT-WAVE is a promising new temporal GPNA algorithm, which efficiently optimizes dynamic NC. Future work on better incorporating dynamic EC may yield further improvements.

Many popular representation-learning algorithms use training objectives defined on the observed data space (which we call "pixel-level"). This may be detrimental when only a small fraction of the bits of signal actually matter at a semantic level. We hypothesize that representations should be learned and evaluated more directly in terms of their information content and statistical or structural constraints. To address the first quality, we consider learning unsupervised representations by maximizing mutual information between part or all of the input and a high-level feature vector. To address the second, we control characteristics of the representation by matching to a prior adversarially. Our method, which we call Deep INFOMAX (DIM), can be used to learn representations with desired characteristics and which empirically outperform a number of popular unsupervised learning methods on classification tasks. DIM opens new avenues for unsupervised learning of representations and is an important step towards flexible formulations of representation-learning objectives catered towards specific end-goals.

Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed identically to the testing data. In many real-world applications, however, some potential training examples are unknown to the modeler, due to sample selection bias or, more generally, covariate shift, i.e., a distribution shift between the training and deployment stage. The resulting discrepancy between training and testing distributions leads to poor generalization performance of the ML model and hence biased predictions. We provide novel algorithms that estimate the number and properties of these unknown training examples---unknown unknowns. This information can then be used to correct the training set, prior to seeing any test data. The key idea is to combine species-estimation techniques with data-driven methods for estimating the feature values for the unknown unknowns. Experiments on a variety of ML models and datasets indicate that taking the unknown examples into account can yield a more robust ML model that generalizes better.

Clustering is an essential data mining tool that aims to discover inherent cluster structure in data. For most applications, applying clustering is only appropriate when cluster structure is present. As such, the study of clusterability, which evaluates whether data possesses such structure, is an integral part of cluster analysis. However, methods for evaluating clusterability vary radically, making it challenging to select a suitable measure. In this paper, we perform an extensive comparison of measures of clusterability and provide guidelines that clustering users can reference to select suitable measures for their applications.

A self-organizing map (SOM) is a type of competitive artificial neural network, which projects the high-dimensional input space of the training samples into a low-dimensional space with the topology relations preserved. This makes SOMs supportive of organizing and visualizing complex data sets and have been pervasively used among numerous disciplines with different applications. Notwithstanding its wide applications, the self-organizing map is perplexed by its inherent randomness, which produces dissimilar SOM patterns even when being trained on identical training samples with the same parameters every time, and thus causes usability concerns for other domain practitioners and precludes more potential users from exploring SOM based applications in a broader spectrum. Motivated by this practical concern, we propose a deterministic approach as a supplement to the standard self-organizing map. In accordance with the theoretical design, the experimental results with satellite cloud data demonstrate the effective and efficient organization as well as simplification capabilities of the proposed approach.

Multi-task clustering (MTC) has attracted a lot of research attentions in machine learning due to its ability in utilizing the relationship among different tasks. Despite the success of traditional MTC models, they are either easy to stuck into local optima, or sensitive to outliers and noisy data. To alleviate these problems, we propose a novel self-paced multi-task clustering (SPMTC) paradigm. In detail, SPMTC progressively selects data examples to train a series of MTC models with increasing complexity, thus highly decreases the risk of trapping into poor local optima. Furthermore, to reduce the negative influence of outliers and noisy data, we design a soft version of SPMTC to further improve the clustering performance. The corresponding SPMTC framework can be easily solved by an alternating optimization method. The proposed model is guaranteed to converge and experiments on real data sets have demonstrated its promising results compared with state-of-the-art multi-task clustering methods.

Trip recommendation is an important location-based service that helps relieve users from the time and efforts for trip planning. It aims to recommend a sequence of places of interest (POIs) for a user to visit that maximizes the user's satisfaction. When adding a POI to a recommended trip, it is essential to understand the context of the recommendation, including the POI popularity, other POIs co-occurring in the trip, and the preferences of the user. These contextual factors are learned separately in existing studies, while in reality, they impact jointly on a user's choice of a POI to visit. In this study, we propose a POI embedding model to jointly learn the impact of these contextual factors. We call the learned POI embedding a context-aware POI embedding. To showcase the effectiveness of this embedding, we apply it to generate trip recommendations given a user and a time budget. We propose two trip recommendation algorithms based on our context-aware POI embedding. The first algorithm finds the exact optimal trip by transforming and solving the trip recommendation problem as an integer linear programming problem. To achieve a high computation efficiency, the second algorithm finds a heuristically optimal trip based on adaptive large neighborhood search. We perform extensive experiments on real datasets. The results show that our proposed algorithms consistently outperform state-of-the-art algorithms in trip recommendation quality, with an advantage of up to 43% in F1-score.

For analytic inference, we will learn to run chi-squared tests. Of course not all survey data are categorical and so in this chapter, we will explore analyzing quantitative survey data. We will learn to compute survey-weighted statistics, such as the mean and quantiles. For data visualization, we'll construct bar-graphs, histograms and density plots. We will close out the chapter by conducting analytic inference with survey-weighted t-tests. To model survey data also requires careful consideration of how the data were collected. We will start our modeling chapter by learning how to incorporate survey weights into scatter plots through aesthetics such as size, color, and transparency. We'll model the survey data with linear regression and will explore how to incorporate categorical predictors and polynomial terms into our models.