Although adversarial examples and model robustness have been extensively studied in the context of linear models and neural networks, research on this issue in tree-based models and how to make tree-based models robust against adversarial examples is still limited. In this paper, we show that tree based models are also vulnerable to adversarial examples and develop a novel algorithm to learn robust trees. At its core, our method aims to optimize the performance under the worst-case perturbation of input features, which leads to a max-min saddle point problem. Incorporating this saddle point objective into the decision tree building procedure is non-trivial due to the discrete nature of trees --- a naive approach to finding the best split according to this saddle point objective will take exponential time. To make our approach practical and scalable, we propose efficient tree building algorithms by approximating the inner minimizer in this saddle point problem, and present efficient implementations for classical information gain based trees as well as state-of-the-art tree boosting models such as XGBoost. Experimental results on real world datasets demonstrate that the proposed algorithms can substantially improve the robustness of tree-based models against adversarial examples.

Carbon-free technologies like renewable energy help combat climate change, but many of them have not reached their full potential. Consider wind power: over the past decade, wind farms have become an important source of carbon-free electricity as the cost of turbines has plummeted and adoption has surged. However, the variable nature of wind itself makes it an unpredictable energy source--less useful than one that can reliably deliver power at a set time. In search of a solution to this problem, last year DeepMind and Google started applying machine learning algorithms to 700 megawatts of wind power capacity in the central United States. These wind farms--part of Google's global fleet of renewable energy projects--collectively generate as much electricity as is needed by a medium-sized city.

In this tutorial, we will discuss an interesting application of Deep Learning applied to faces. We will estimate the age and figure out the gender of ...

Wind power has become increasingly popular, but its success is limited by the fact that wind comes and goes as it pleases, making it hard for power grids to count on the renewable energy and less likely to fully embrace it. While we can't control the wind, Google has an idea for the next best thing: using machine learning to predict it. Google and DeepMind have started testing machine learning on Google's own wind turbines, which are part of the company's renewable energy projects. Beginning last year, they fed weather forecasts and existing turbine data into DeepMind's machine learning platform, which churned out wind power predictions 36 hours ahead of actual power generation. Google could then make supply commitments to power grids a full day before delivery.

Learn Convolutional Neural Networks for Visual Recognition and the building blocks and methods associated with them. Deep Learning has made some huge and significant contributions and it's one of the mostly adopted techniques in order to drive insights from your data nowadays. Convolutional neural networks have gained a special status over the last few years as an especially promising form of deep learning. Rooted in image processing, convolutional layers have found their way into virtually all subfields of deep learning, and are very successful for the most part. Convolutional Neural Networks are very similar to ordinary Neural Networks: they are made up of neurons that have learnable weights and biases.

OpenAI has the entire AI community debating its decision to not release the fully trained version of its powerful new text generator model dubbed GPT-2. I'm going to explain how GPT-2 works using code, math, and animations. We'll discuss its potential applications (both good and bad), ways of preventing misuse, and at the end of the video I'll give my take on whether OpenAI was justified in doing so. The transformer architecture is quickly replacing recurrent networks for sequence learning, and OpenAI's GPT-2 is the latest example of using it at scale. Thats what keeps me going.

Ensuring fairness and safety in artificial intelligence(AI) applications is considered by many the biggest challenge in the space. As AI systems match or surpass human intelligence in many areas, it is essential that we establish a guideline to align this new form of intelligence with human values. The challenge is that, as humans, we understand very little about how our values are represented in the brain or we can't even formulate specific rules to describe a specific value. While AI operates in a data universe, human values are a byproduct of our evolution as social beings. We don't describe human values like fairness or justice using neuroscientific terms but using arguments from social sciences like psychology, ethics or sociology Recently, researchers from OpenAI published a paper describing the importance of social sciences to improve the safety and fairness or AI algorithms in processes that require human intervention.

In this book, the first four chapters are provided as a guide for teachers who want to use the book for teacher training and development. Using the tools, tips and activities provided in these first chapters a teacher with some basic experience of using technology in the classroom should be able to create motivating hands-on edtech training for their peers or for pre-service trainee teachers.

For newbies, starting to learn machine learning can be painful if they don't have right resources to learn from. Most of the machine learning libraries are difficult to understand and learning curve can be a bit frustrating. I am creating a repository on Github(cheatsheets-ai) containing cheatsheets for different machine learning frameworks, gathered from different sources. Do visit the Github repository, also, contribute cheat sheets if you have any.

It is actually a Matrix manipulation library, and this difference is significant. NeurIPS 2018., the authors demonstrate that their automatic differentiation library based on actual Tensor Calculus has significantly more compact expression trees. This is because Tensor Calculus uses index notation, which results in treating both the forward mode and the reverse mode in the same manner. By contrast, Matrix Calculus hides the indices for notational convenience, and this often results in overly complicated automatic differentiation expression trees. Consider the matrix multiplication .