Multi-label learning studies the problem where an instance is associated with a set of labels. By treating single-label learning problem as one task, the multi-label learning problem can be casted as solving multiple related tasks simultaneously. In this paper, we propose a novel Multi-task Gradient Descent (MGD) algorithm to solve a group of related tasks simultaneously. In the proposed algorithm, each task minimizes its individual cost function using reformative gradient descent, where the relations among the tasks are facilitated through effectively transferring model parameter values across multiple tasks. Theoretical analysis shows that the proposed algorithm is convergent with a proper transfer mechanism. Compared with the existing approaches, MGD is easy to implement, has less requirement on the training model, can achieve seamless asymmetric transformation such that negative transfer is mitigated, and can benefit from parallel computing when the number of tasks is large. The competitive experimental results on multi-label learning datasets validate the effectiveness of the proposed algorithm.

MANGA: Method Agnostic Neural-policy Generalization and Adaptation Homanga Bharadhwaj 1, Shoichiro Y amaguchi 2, and Shin-ichi Maeda 2 Abstract -- In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework that decouples the processes of policy learning and system identification. Efficiently transferring learned policies to an unknown environment with changes in dynamics configurations in the presence of motor noise is very important for operating robots in the real world, and our work is a novel attempt in that direction. We introduce MANGA: Method Agnostic Neural-policy Generalization and Adaptation, that trains dynamics conditioned policies and efficiently learns to estimate the dynamics parameters of the environment given off-policy state-transition rollouts in the environment. Our scheme is agnostic to the type of training method used - both reinforcement learning (RL) and imitation learning (IL) strategies can be used. We demonstrate the effectiveness of our approach by experimenting with four different MuJoCo agents and comparing against previously proposed transfer baselines. I NTRODUCTION One of the most well recognized goals of robotics research is to develop autonomous agents that can perform a wide variety of tasks in various complex environments. Recently numerous deep reinforcement learning (RL) and imitation learning (IL) based approaches have sought to achieve good performance in complex robotic tasks through minimal supervision. However, a major concern in experimenting with the real environment directly is safety, both of the robot and of the environment. Safety concerns and also the issue of reproducibility has drawn robotics research extensively to simulation environments.

Machine learning and deep learning have been widely embraced, and even more widely misunderstood. In this article, I'd like to step back and explain both machine learning and deep learning in basic terms, discuss some of the most common machine learning algorithms, and explain how those algorithms relate to the other pieces of the puzzle of creating predictive models from historical data. Recall that machine learning is a class of methods for automatically creating models from data. Machine learning algorithms are the engines of machine learning, meaning it is the algorithms that turn a data set into a model. Which kind of algorithm works best (supervised, unsupervised, classification, regression, etc.) depends on the kind of problem you're solving, the computing resources available, and the nature of the data.

Despite the success of supervised machine learning and deep learning, there's a school of thought that says that unsupervised learning has even greater potential. The learning of a supervised learning system is limited by its training; i.e., a supervised learning system can learn only those tasks that it's trained for. By contrast, an unsupervised system could theoretically achieve "artificial general intelligence," meaning the ability to learn any task a human can learn. If the biggest problem with supervised learning is the expense of labeling the training data, the biggest problem with unsupervised learning (where the data is not labeled) is that it often doesn't work very well. Nevertheless, unsupervised learning does have its uses: It can sometimes be good for reducing the dimensionality of a data set, exploring the pattern and structure of the data, finding groups of similar objects, and detecting outliers and other noise in the data.

How to Make AdaBoost.M1 Work for Weak Base Classifiers by Changing Only One Line of the Code (ECML 2002)

Machine learning (ML) is the current paradigm for modeling statistical phenomena by harnessing algorithms that exploit computer intelligence. It is common place to build ML models that predict housing prices, aggregate users by their potential marketing interests, and use image recognition techniques to identify brain tumors. However, up until now these models have required scrupulous trial and error in order to optimize model performance on unseen data. The advent of automated machine learning (AutoML) aims to curb the resources required (time and expertise) by offering well-designed pipelines that handle data preprocessing, feature selection, and model creation and evaluation. While AutoML may initially only appeal to enterprises that want to harness the power of ML without consuming precious budgets and hiring skilled data practitioners, it also contains very strong promise to become an invaluable tool for the experienced data scientist.

Data science or data-driven science enables better decision making, predictive analysis, and pattern discovery. In practice, data science is already helping the airline industry predict disruptions in travel to alleviate the pain for both airlines and passengers. In another example, let's say you want to buy new furniture for your office. When looking online for the best option and deal, you should answer some critical questions before making your decision. Using this sample decision tree, you can narrow down your selection to a few websites and, ultimately, make a more informed final decision.

The Center for Advanced Electronics through Machine Learning (CAEML) has been very active in the newly-established machine learning track at DesignCon, helping to present many quality papers from the hardware design community. Celebrating its third anniversary this year, CAEML has been at the forefront of machine learning and its applications in hardware and electronic design. Much of the center's research has direct applications in the area of hardware and device management through machine-learned inference – from proactive hardware failure predictions, to complex performance modeling through surrogate models, to high dimensional time series prediction for resource forecasting. This article will take a look at some of the results of this research and its applications for AI-defined, next-generation hardware platforms. There has been an explosive growth of Internet of Things (IoT) devices in recent years. Analysts at Gartner predict the IoT will produce about $2 trillion US in economic benefit in the next five to 10 years.

Unfortunately, the reality is a little bit different, in particular in deep models, where the number of parameters is in the order of ten or one hundred million. When the system is relatively shallow, it's easier to find local minima where the training process can stop, while in deeper models, the probability of a local minimum becomes smaller and, instead, saddle points become more and more likely.

Time series classification problems have drawn increasing attention in the machine learning and statistical community. Closely related is the field of functional data analysis (FDA): it refers to the range of problems that deal with the analysis of data that is continuously indexed over some domain. While often employing different methods, both fields strive to answer similar questions, a common example being classification or regression problems with functional covariates. We study methods from functional data analysis, such as functional generalized additive models, as well as functionality to concatenate (functional-) feature extraction or basis representations with traditional machine learning algorithms like support vector machines or classification trees. In order to assess the methods and implementations, we run a benchmark on a wide variety of representative (time series) data sets, with in-depth analysis of empirical results, and strive to provide a reference ranking for which method(s) to use for non-expert practitioners. Additionally, we provide a software framework in R for functional data analysis for supervised learning, including machine learning and more linear approaches from statistics. This allows convenient access, and in connection with the machine-learning toolbox mlr, those methods can now also be tuned and benchmarked.