The rapid development of deep learning methods has permitted the fast and accurate medical decision making from complex structured data, like CT images or MRI. However, some problems still exist in such applications that may lead to imperfect predictions. Previous observations have shown that, confounding factors, if handled inappropriately, will lead to biased prediction results towards some major properties of the data distribution. In other words, naïvely applying deep learning methods in these applications will lead to unfair prediction results for the minority group defined by the characteristics including age, gender, or even the hospital that collects the data, etc. In this paper, extending previous successes in correcting confounders, we propose a more stable method, namely Confounder Filtering, that can effectively reduce the influence of confounding factors, leading to better generalizability of trained discriminative deep neural networks, therefore, fairer prediction results. Our experimental results indicate that the Confounder Filtering method is able to improve the performance for different neural networks including CNN, LSTM, and other arbitrary architecture, different data types including CTscan, MRI, and EEG brain wave data, as well as different confounding factors including age, gender, and physical factors of medical devices etc.

We uncover a fairly general principle in online learning: If regret can be (approximately) expressed as a function of certain "sufficient statistics" for the data sequence, then there exists a special Burkholder function that 1) can be used algorithmically to achieve the regret bound and 2) only depends on these sufficient statistics, not the entire data sequence, so that the online strategy is only required to keep the sufficient statistics in memory. This characterization is achieved by bringing the full power of the Burkholder Method --- originally developed for certifying probabilistic martingale inequalities --- to bear on the online learning setting. To demonstrate the scope and effectiveness of the Burkholder method, we develop a novel online strategy for matrix prediction that attains a regret bound corresponding to the variance term in matrix concentration inequalities. We also present a linear-time/space prediction strategy for parameter free supervised learning with linear classes and general smooth norms.

Paperspace offers multiple templates for you to start. I recommend using the fast.ai This template is intended to provide a fully functional machine learning environment for interactive development. The template includes NVIDIA's libraries for using the GPU to run Machine Learning programs, as well as a variety of libraries for ML development (Anaconda Python distribution, Jupyter notebook, fast.ai Due to high demand, your request might take a few hours to be completed.

Linear algebra is a field of applied mathematics that is a prerequisite to reading and understanding the formal description of deep learning methods, such as in papers and textbooks. Generally, an understanding of linear algebra (or parts thereof) is presented as a prerequisite for machine learning. Although important, this area of mathematics is seldom covered by computer science or software engineering degree programs. In this post, you will discover the crash course in linear algebra for deep learning presented in the de facto textbook on deep learning. Linear Algebra for Deep Learning Photo by Quinn Dombrowski, some rights reserved.

A robotic hand that can translate words into sign language gestures for deaf people has been created by scientists. Named Project Aslan, the 3D-printed hand costs as little as £400 ($560) to make and interprets both written text and spoken words. The device communicates through'fingerspelling', a type of sign language where words are spelled out letter-by-letter through separate gestures on a single hand. The robot, which will be ready in five years, could one day be carried around in a rucksack, scientists say. It could help some of the 70 million worldwide who are deaf or hard of hearing to communicate with people who don't know sign language.

If you are a developer, a random tech interested person or you don't have anything to do with tech, you must have heard phrase machine learning many many times in past few years. You can read about it on blogs, in newspapers, on TV and even when going to the supermarket. It looks like machine learning is one of those buzzwords that is buzzing and buzzing. One reason is that there are some people, companies that are using machine learning for solving cool and serious problems. They are solving things that were not solvable before, taking a different approach to all sorts of topics.

Businessman on blurred background using digital artificial intelligence (AI) interface 3D rendering. An artificial intelligence (AI) and Blockchain start-up with backing from Harrisburg University in Pennsylvania is developing a completely new way of utilizing and processing data by integrating AI and "smart logic" into every bit of data. The goal is to build what is described as an "AI Superhighway" according to the tech protagonists with the vision behind the project. Essentially, the proposition goes that by embedding every piece of data with artificial intelligence, otherwise "dumb data", which requires an application to become useful, becomes valuable and "smart." This means the "AI Thought" attaches to data allows the digital information to act on its own.

Artificial Intelligence seems to be reinforcing gender stereotypes. In 2016, a university professor from Virginia noticed that the image recognition system he was working on often associated picture of kitchens with women. Intrigued, he and his colleagues tested large collections of photos used to train this kind of software. What they discovered was shocking. The software's depiction of common activities showed a definite gender bias.

The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem settings and it has been receiving increasing attention from the scientific community, leading to some high-profile success stories such as the much publicized Deep Q-Networks (DQN). In this article we take a big picture look at how the ALE is being used by the research community. We show how diverse the evaluation methodologies in the ALE have become with time, and highlight some key concerns when evaluating agents in the ALE. We use this discussion to present some methodological best practices and provide new benchmark results using these best practices. To further the progress in the field, we introduce a new version of the ALE that supports multiple game modes and provides a form of stochasticity we call sticky actions. We conclude this big picture look by revisiting challenges posed when the ALE was introduced, summarizing the state-of-the-art in various problems and highlighting problems that remain open.

Ensemble methods -- particularly those based on decision trees -- have recently demonstrated superior performance in a variety of machine learning settings. Specifically, Random Forest (RF) was found to outperform >100 other methods in several manuscripts, and gradient boosting trees have been a crucial component of several recent Kaggle competition victories. Building off these successes and recent advances in sparse learning and random matrix theory, we propose a novel ensemble tree method called "Randomer Forest" (RerF). The key intuition behind RerF is that we can use sparse linear combinations at each decision node rather than just one feature (as in RF) or all of them (as in Rotation Forests). RerF significantly outperforms other methods on a standard benchmark suite containing 105 problems with varying dimension, sample size, and number of classes. Moreover, we provide an implementation that scales as or more efficiently than other available packages. Via a combination of basic principles, theory, and extensive numerical experiments, we demonstrate why, when, and how RerF achieves its performance properties.