Regression problems assume every instance is annotated (labeled) with a real value, a form of annotation we call \emph{strong guidance}. In order for these annotations to be accurate, they must be the result of a precise experiment or measurement. However, in some cases additional \emph{weak guidance} might be given by imprecise measurements, a domain expert or even crowd sourcing. Current formulations of regression are unable to use both types of guidance. We propose a regression framework that can also incorporate weak guidance based on relative orderings, bounds, neighboring and similarity relations. Consider learning to predict ages from portrait images, these new types of guidance allow weaker forms of guidance such as stating a person is in their 20s or two people are similar in age. These types of annotations can be easier to generate than strong guidance. We introduce a probabilistic formulation for these forms of weak guidance and show that the resulting optimization problems are convex. Our experimental results show the benefits of these formulations on several data sets.

As wireless networks evolve towards high mobility and providing better support for connected vehicles, a number of new challenges arise due to the resulting high dynamics in vehicular environments and thus motive rethinking of traditional wireless design methodologies. Future intelligent vehicles, which are at the heart of high mobility networks, are increasingly equipped with multiple advanced onboard sensors and keep generating large volumes of data. Machine learning, as an effective approach to artificial intelligence, can provide a rich set of tools to exploit such data for the benefit of the networks. In this article, we first identify the distinctive characteristics of high mobility vehicular networks and motivate the use of machine learning to address the resulting challenges. After a brief introduction of the major concepts of machine learning, we discuss its applications to learn the dynamics of vehicular networks and make informed decisions to optimize network performance. In particular, we discuss in greater detail the application of reinforcement learning in managing network resources as an alternative to the prevalent optimization approach. Finally, some open issues worth further investigation are highlighted.

Sparse principal component analysis (SPCA) has emerged as a powerful technique for modern data analysis. We discuss a robust and scalable algorithm for computing sparse principal component analysis. Specifically, we model SPCA as a matrix factorization problem with orthogonality constraints, and develop specialized optimization algorithms that partially minimize a subset of the variables (variable projection). The framework incorporates a wide variety of sparsity-inducing regularizers for SPCA. We also extend the variable projection approach to robust SPCA, for any robust loss that can be expressed as the Moreau envelope of a simple function, with the canonical example of the Huber loss. Finally, randomized methods for linear algebra are used to extend the approach to the large-scale (big data) setting. The proposed algorithms are demonstrated using both synthetic and real world data.

We address a largely open problem of multilabel classification over graphs. Unlike traditional vector input, a graph has rich variable-size structures, that suggests complex relationships between labels and subgraphs. Uncovering these relations might hold the keys of classification performance and explainability. To this end, we design GAML (Graph Attentional Multi-Label learning), a graph neural network that models the relations present in the input graph, in the label set, and across graph-labels by leveraging the message passing algorithm and attention mechanism. Representation of labels and input nodes is refined iteratively through multiple steps, during which interesting subgraph-label patterns emerge. In addition, GAML is highly flexible by allowing explicit label dependencies to be incorporated easily. It also scales linearly with the number of labels and graph size thanks to our proposed hierarchical attention. These properties open a wide range of applications seen in the real world. We evaluate GAML on an extensive set of experiments with both graph inputs (for predicting drug-protein binding, and drug-cancer response), and classical unstructured inputs. The results are significantly better than well-known multilabel learning techniques.

Linear regression models are not perfect. It tries to approximate the relationship between dependent and independent variables in a straight line. Some errors can be reduced. Some errors are inherent in the nature of the problem. These errors cannot be eliminated. They are called as an irreducible error, the noise term in the true relationship that cannot fundamentally be reduced by any model.

This article will portray how data related to diabetes can be leveraged to predict if a person has diabetes or not. More specifically, this article will focus on how machine learning can be utilized to predict diseases such as diabetes. By the end of this article series you will be able to understand concepts like data exploration, data cleansing, feature selection, model selection, model evaluation and apply them in a practical way. Diabetes is a disease which occurs when the blood glucose level becomes high, which ultimately leads to other health problems such as heart diseases, kidney disease etc. Diabetes is caused mainly due to the consumption of highly processed food, bad consumption habits etc. According to WHO, the number of people with diabetes has been increased over the years.

Dealing with the shear size and complexity of today's massive data sets requires computational platforms that can analyze data in a parallelized and distributed fashion. A major bottleneck that arises in such modern distributed computing environments is that some of the worker nodes may run slow. These nodes a.k.a.~stragglers can significantly slow down computation as the slowest node may dictate the overall computational time. A recent computational framework, called encoded optimization, creates redundancy in the data to mitigate the effect of stragglers. In this paper we develop novel mathematical understanding for this framework demonstrating its effectiveness in much broader settings than was previously understood. We also analyze the convergence behavior of iterative encoded optimization algorithms, allowing us to characterize fundamental trade-offs between convergence rate, size of data set, accuracy, computational load (or data redundancy), and straggler toleration in this framework.

A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this goal is approached by minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations useful for subsequent tasks will arise as a side effect. In this work, we propose instead to directly target a later desired task by meta-learning an unsupervised learning rule, which leads to representations useful for that task. Here, our desired task (meta-objective) is the performance of the representation on semi-supervised classification, and we meta-learn an algorithm -- an unsupervised weight update rule -- that produces representations that perform well under this meta-objective. Additionally, we constrain our unsupervised update rule to a be a biologically-motivated, neuron-local function, which enables it to generalize to novel neural network architectures. We show that the meta-learned update rule produces useful features and sometimes outperforms existing unsupervised learning techniques. We show that the meta-learned unsupervised update rule generalizes to train networks with different widths, depths, and nonlinearities. It also generalizes to train on data with randomly permuted input dimensions and even generalizes from image datasets to a text task.

We present a neurosymbolic approach to the lifelong learning of algorithmic tasks that mix perception and procedural reasoning. Reusing highlevel concepts across domains and learning complex procedures are two key challenges in lifelong learning. We show that a combination of gradientbased learning and symbolic program synthesis can be a more effective response to these challenges than purely neural methods. Concretely, our approach, called HOUDINI, represents neural networks as strongly typed, end-to-end differentiable functional programs that use symbolic higher-order combinators to compose a library of neural functions. Our learning algorithm consists of: (1) a program synthesizer that performs a type-directed search over programs in this language, and decides on the library functions that should be reused and the architectures that should be used to combine them; and (2) a neural module that trains synthesized programs using stochastic gradient descent. We evaluate our approach on three algorithmic tasks. Our experiments show that our type-directed search technique is able to significantly prune the search space of programs, and that the overall approach transfers high-level concepts more effectively than monolithic neural networks as well as traditional transfer learning.

Want to watch this again later? Sign in to add this video to a playlist. Report Need to report the video? Sign in to report inappropriate content. Report Need to report the video?