Data Science is an interdisciplinary field that employs techniques to extract knowledge from data. As one of the fast growing fields in technology, the interest for Data Science is booming, and the demand for specialized talent is on the rise. This course takes a practical approach to Data Science, presenting solutions for common and not-so-common problems in the form of recipes. This video will begin from exploring your data using the different methods like data acquisition, data cleaning, data mining, machine learning, and data visualization, applied to a variety of different data types like structured data or free-form text. It will show how to deal with text using different methods like text normalization and calculating word frequencies.

Bitcoin and blockchain entered the consumer lexicon in a media frenzy that saw it hit $19,000 USD per coin (albeit for only 20 minutes) and led thousands of new hopefuls to Google'what is bitcoin and how will it make me rich?' And the WannaCry cyberattack saw consumers' cherished photos and documents held to ransom, crippling Britain's NHS and reminding everyone that cybersecurity isn't just for big corporations or spy agencies. With all of that in mind, along with Niels Bohr's observation that prediction is very difficult (especially about the future), here are our six predictions about how these key themes -- AI and Machine Learning (ML), IoT, security, blockchain -- are likely to begin to make a real difference in the way all of us interact with technology in 2018… Ever tried to use Siri offline? Suddenly, your knowledgeable little friend becomes rather dumb. In 2017, AI fed consumers content on Facebook or Netflix while assistants such as Siri, Alexa or Google Assistant identified what song was playing or what the weather would be like tomorrow.

A few weeks ago I went to the Imperial War Museum in London to watch an artificial intelligence program attempt to crack the mindbendingly complex Enigma code used by the Germans during the second world war. It did so in 12 minutes and 50 seconds. Having already machine read some German language training data from Grimm's Fairy Tales, the AI program crunched through billions of permutations generated by the four-rotor Enigma machine sifting combinations of letters for their "Germanness". A challenge that had occupied some of Britain's most brilliant mathematical minds at Bletchley Park for many months and at enormous cost was solved by a modern AI program in a few minutes for only £10. The program, developed by the data analytics company Enigma Pattern and boosted by 2,000 virtual servers, was able to check an astonishing 41m combinations a second.

In biostatistics, propensity score is a common approach to analyze the imbalance of covariate and process confounding covariates to eliminate differences between groups. While there are an abundant amount of methods to compute propensity score, a common issue of them is the corrupted labels in the dataset. For example, the data collected from the patients could contain samples that are treated mistakenly, and the computing methods could incorporate them as a misleading information. In this paper, we propose a Machine Learning-based method to handle the problem. Specifically, we utilize the fact that the majority of sample should be labeled with the correct instance and design an approach to first cluster the data with spectral clustering and then sample a new dataset with a distribution processed from the clustering results. The propensity score is computed by Xgboost, and a mathematical justification of our method is provided in this paper. The experimental results illustrate that xgboost propensity scores computing with the data processed by our method could outperform the same method with original data, and the advantages of our method increases as we add some artificial corruptions to the dataset. Meanwhile, the implementation of xgboost to compute propensity score for multiple treatments is also a pioneering work in the area. Introduction Confounding covariates, or alternatively named as noise features, is a significant problem in studying Biostatistics data. In practice, data in this field is usually collected with detailed information, thus it will contain some irrelevant and redundant features.

In this work we propose a data-driven modelization approach for the management of advertising investments of a firm. First, we propose an application of dynamic linear models to the prediction of an economic variable, such as global sales, which can use information from the environment and the investment levels of the company in different channels. After we build a robust and precise model, we propose a metric of risk, which can help the firm to manage their advertisement plans, thus leading to a robust, risk-aware optimization of their revenue. The advertising industry represents an estimate of US$ 529.43 billion [4] and this quantity is likely to increase in the following years. In parallel, there has been a recent interest in the application of data-driven models in the context of forecasting and decision making in the marketing industry.

The analysis of continously larger datasets is a task of major importance in a wide variety of scientific fields. In this sense, cluster analysis algorithms are a key element of exploratory data analysis, due to their easiness in the implementation and relatively low computational cost. Among these algorithms, the K -means algorithm stands out as the most popular approach, besides its high dependency on the initial conditions, as well as to the fact that it might not scale well on massive datasets. In this article, we propose a recursive and parallel approximation to the K -means algorithm that scales well on both the number of instances and dimensionality of the problem, without affecting the quality of the approximation. In order to achieve this, instead of analyzing the entire dataset, we work on small weighted sets of points that mostly intend to extract information from those regions where it is harder to determine the correct cluster assignment of the original instances. In addition to different theoretical properties, which deduce the reasoning behind the algorithm, experimental results indicate that our method outperforms the state-of-the-art in terms of the trade-off between number of distance computations and the quality of the solution obtained.

Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems. Backpropagation through time is the algorithm that is commonly used to train these networks on specific tasks. Many deep learning frameworks have their own implementation of training and sampling procedures for recurrent neural networks, while there are in fact multiple other possibilities to choose from and other parameters to tune. In existing literature this is very often overlooked or ignored. In this paper we therefore give an overview of possible training and sampling schemes for character-level recurrent neural networks to solve the task of predicting the next token in a given sequence. We test these different schemes on a variety of datasets, neural network architectures and parameter settings, and formulate a number of take-home recommendations. The choice of training and sampling scheme turns out to be subject to a number of trade-offs, such as training stability, sampling time, model performance and implementation effort, but is largely independent of the data. Perhaps the most surprising result is that transferring hidden states for correctly initializing the model on subsequences often leads to unstable training behavior depending on the dataset.

A research team from a hospital in Oxford have created artificial intelligence that can diagnose scans for lung cancer and heart disease. The AI system will reportedly help in saving billions of dollars by helping to diagnose the diseases much earlier. NHS hospitals can avail the technology for free, beginning summer 2018, and AI could help in saving the NHS. "There is about £2.2bn spent on pathology services in the NHS. You may be able to reduce that by 50%," said immunologist Sir John Bell.

Automotive supplier Bosch wants to help guide drivers to vacant parking spots in more than a dozen U.S. cities this year. The German company says it's been testing its "community-based parking" initiative in Stuttgart and other German cities and will launch it later this year in as many as 20 U.S. cities, including Los Angeles, Miami and Boston. The company says it will be working with automakers on the initiative but didn't say which ones. As cars drive by, they will automatically recognize and measure gaps between parked cars and transmit that data to a digital map. The company has been pushing a number of smart-city projects, including internet-connected sensors to monitor pollution, allergens and flooding.

I am still working on this, but now many more people are interested. Because the methods we've created on the way to this goal are now permeating the modern world--available to half of humankind, used billions of times per day.