Many real-world large-scale regression problems can be formulated as Multi-task Learning (MTL) problems with a massive number of tasks, as in retail and transportation domains. However, existing MTL methods still fail to offer both the generalization performance and the scalability for such problems. Scaling up MTL methods to problems with a tremendous number of tasks is a big challenge. Here, we propose a novel algorithm, named Convex Clustering Multi-Task regression Learning (CCMTL), which integrates with convex clustering on the k-nearest neighbor graph of the prediction models. Further, CCMTL efficiently solves the underlying convex problem with a newly proposed optimization method. CCMTL is accurate, efficient to train, and empirically scales linearly in the number of tasks. On both synthetic and real-world datasets, the proposed CCMTL outperforms seven state-of-the-art (SoA) multi-task learning methods in terms of prediction accuracy as well as computational efficiency. On a real-world retail dataset with 23, 812 tasks, CCMTL requires only around 30 seconds to train on a single thread, while the SoA methods need up to hours or even days.

In late winter of 1975, a scrap of paper started appearing on bulletin boards around the San Francisco Peninsula. "Are you building your own computer?" it asked. If so, you might like to come to a gathering." The invite drew 32 people to a Menlo Park, California, garage for the first meeting of the Homebrew Computer Club, a community of hobbyists intrigued by the potential of a newly affordable component called the microprocessor. One was a young engineer named Steve Wozniak, who later brought a friend named Steve Jobs into the club.

The first programming exercise "Twitter Sentiment Analysis in Python" is both fun and challenging, where you analyze tons of twitter message to find out the sentiments e.g.

Given that South African education is in crisis, strategies for improvement and sustainability of high-quality, up-to-date education must be explored. In the migration of education online, inclusion of machine translation for low-resourced local languages becomes necessary. This paper aims to spur the use of current neural machine translation (NMT) techniques for low-resourced local languages. The paper demonstrates state-of-the-art performance on English-to-Setswana translation using the Autshumato dataset. The use of the Transformer architecture beat previous techniques by 5.33 BLEU points. This demonstrates the promise of using current NMT techniques for African languages.

We propose a general theoretical method for analyzing the risk bound in the presence of adversaries. In particular, we try to fit the adversarial learning problem into the minimax framework. We first show that the original adversarial learning problem could be reduced to a minimax statistical learning problem by introducing a transport map between distributions. Then we prove a risk bound for this minimax problem in terms of covering numbers. In contrast to previous minimax bounds in \cite{lee,far}, our bound is informative when the radius of the ambiguity set is small. Our method could be applied to multi-class classification problems and commonly-used loss functions such as hinge loss and ramp loss. As two illustrative examples, we derive the adversarial risk bounds for kernel-SVM and deep neural networks. Our results indicate that a stronger adversary might have a negative impact on the complexity of the hypothesis class and the existence of margin could serve as a defense mechanism to counter adversarial attacks.

We introduce the community exploration problem that has many real-world applications such as online advertising. In the problem, an explorer allocates limited budget to explore communities so as to maximize the number of members he could meet. We provide a systematic study of the community exploration problem, from offline optimization to online learning. For the offline setting where the sizes of communities are known, we prove that the greedy methods for both of non-adaptive exploration and adaptive exploration are optimal. For the online setting where the sizes of communities are not known and need to be learned from the multi-round explorations, we propose an `upper confidence' like algorithm that achieves the logarithmic regret bounds. By combining the feedback from different rounds, we can achieve a constant regret bound.

Anomaly detection in supercomputers is a very difficult problem due to the big scale of the systems and the high number of components. The current state of the art for automated anomaly detection employs Machine Learning methods or statistical regression models in a supervised fashion, meaning that the detection tool is trained to distinguish among a fixed set of behaviour classes (healthy and unhealthy states). We propose a novel approach for anomaly detection in High Performance Computing systems based on a Machine (Deep) Learning technique, namely a type of neural network called autoencoder. The key idea is to train a set of autoencoders to learn the normal (healthy) behaviour of the supercomputer nodes and, after training, use them to identify abnormal conditions. This is different from previous approaches which where based on learning the abnormal condition, for which there are much smaller datasets (since it is very hard to identify them to begin with). We test our approach on a real supercomputer equipped with a fine-grained, scalable monitoring infrastructure that can provide large amount of data to characterize the system behaviour. The results are extremely promising: after the training phase to learn the normal system behaviour, our method is capable of detecting anomalies that have never been seen before with a very good accuracy (values ranging between 88% and 96%).

Scientists have taught a robot how to use human-like hand gestures while speaking by feeding it footage of people giving presentations. The android learned to use a pointing gesture to portray'you' or'me', as well as a crooked arm action to suggest holding something. Building robots that gesticulate like humans will make interactions with them feel more natural, the Korean team behind the technology said. They built the robot around machine learning software that they showed 52 hours of TED talks - presentations given by expert speakers on various topics. Pictured is a Pepper robot that scientists taught to give human-like hand gestures during speech.

Welcome to our 7-part mini-course on data science and applied machine learning! Over these 7 chapters, our goal is to provide you with an end-to-end blueprint for applied machine learning, while keeping this as actionable and succinct as possible. With that, let's get started with a bird's eye view of the machine learning workflow. One really cool (optional) challenge you can do in the next hour is training your first machine learning model! That's right, we've put together a complete step-by-step tutorial for training a model that can predict wine quality.

It's definitely a great direction to pursue for many businesses since it gives them the ability to deliver tremendous value in a fairly quick and easy way. The demand for machine learning skills is at an all time high. There's a nice comprehensive report done by McKinsey about how AI is shaping industries and where the opportunities are. But wait just a minute… As a business, do you really need a machine learning research team? How much do you even need Machine Learning at all?