As a Christmas present to the world, Finland is making its online crash course in artificial intelligence available to everyone for free. The Nordic nation launched the 6-week "Elements of AI" course last year as a means of educating their citizens on the revolutionary new technology. Since Finland will be passing on its rotating EU presidency to another member state at the end of the year, the country decided to graciously celebrate the occasion by translating the course materials into English, Swedish, Estonian, and German--as well as Finnish--and making it available for EU citizens to take (although there are no geographical limitations on who can take the course). The course, which has thus far been taken by more than 220,000 students from about 110 countries, has become the most popular course offered by the University of Helsinki. It consists of seven modules, each of which takes about 5 to 10 hours to complete.

Created by Lazy Programmer Inc. English [Auto-generated], Spanish [Auto-generated] Created by Lazy Programmer Inc.

The ground breaking advancements in Artificial Intelligence (AI) is creating tremendous opportunities for transforming industries and virtually every aspect of our existence. The demand for people well versed with AI skill-set is exploding and it is expected to generate over 50 million new jobs in the coming years. There are thousands of educational materials out there for learning Artificial Intelligence (AI). However, much of AI Tutorials and Courses are without Graded Assignments or Peer Feedback and have a poor quality. So, I decided to inspire your AI journey by compiling the best courses from the world-class educators, so that you can learn to create AI powered applications that can give you an edge in becoming a skilled AI -- Engineer/ Scientist/ Researcher/ Practitioner.

Model-free Reinforcement Learning (RL) algorithms work well in sequential decision-making problems when experience can be collected cheaply and model-based RL is effective when system dynamics can be modeled accurately. However, both of these assumptions can be violated in real world problems such as robotics, where querying the system can be prohibitively expensive and real-world dynamics can be difficult to model accurately. Although sim-to-real approaches such as domain randomization attempt to mitigate the effects of biased simulation, they can still suffer from optimization challenges such as local minima and hand-designed distributions for randomization, making it difficult to learn an accurate global value function or policy that directly transfers to the real world. In contrast to RL, Model Predictive Control (MPC) algorithms use a simulator to optimize a simple policy class online, constructing a closed-loop controller that can effectively contend with real-world dynamics. MPC performance is usually limited by factors such as model bias and the limited horizon of optimization. In this work, we present a novel theoretical connection between information theoretic MPC and entropy regularized RL and develop a Q-learning algorithm that can leverage biased models. We validate the proposed algorithm on sim-to-sim control tasks to demonstrate the improvements over optimal control and reinforcement learning from scratch. Our approach paves the way for deploying reinforcement learning algorithms on real-robots in a systematic manner.

Complementary-label learning is a new weakly-supervised learning framework that solves the problem where each training example is supplied with a complementary label, which only specifies one of the classes that the example does \textsl{not} belong to. Although a few works have demonstrated that an unbiased estimator of the original classification risk can be obtained from only complementarily labeled data, they are all restricted to the case where each example is associated with exactly one complementary label. It would be more promising to learn from multiple complementary labels simultaneously, as the supervision information would be richer if more complementary labels are provided. So far, whether there exists an unbiased risk estimator for learning from multiple complementary labels simultaneously is still unknown. In this paper, we will give an affirmative answer by deriving the first unbiased risk estimator for learning from multiple complementary labels. In addition, we further theoretically analyze the estimation error bound of our proposed approach, and show that the optimal parametric convergence rate is achieved. Finally, we experimentally demonstrate the effectiveness of the proposed approach.

We investigate heterogenous employment effects of Flemish training programmes. Based on administrative individual data, we analyse programme effects at various aggregation levels using Modified Causal Forests (MCF), a causal machine learning estimator for multiple programmes. While all programmes have positive effects after the lock-in period, we find substantial heterogeneity across programmes and types of unemployed. Simulations show that assigning unemployed to programmes that maximise individual gains as identified in our estimation can considerably improve effectiveness. Simplified rules, such as one giving priority to unemployed with low employability, mostly recent migrants, lead to about half of the gains obtained by more sophisticated rules.

Understanding stories is a challenging reading comprehension problem for machines as it requires reading a large volume of text and following long-range dependencies. In this paper, we introduce the Shmoop Corpus: a dataset of 231 stories that are paired with detailed multi-paragraph summaries for each individual chapter (7,234 chapters), where the summary is chronologically aligned with respect to the story chapter. From the corpus, we construct a set of common NLP tasks, including Cloze-form question answering and a simplified form of abstractive summarization, as benchmarks for reading comprehension on stories. We then show that the chronological alignment provides a strong supervisory signal that learning-based methods can exploit leading to significant improvements on these tasks. We believe that the unique structure of this corpus provides an important foothold towards making machine story comprehension more approachable.

Urban air pollution has been linked to various human health concerns, including cardiopulmonary diseases. Communities who suffer from poor air quality often rely on experts to identify pollution sources due to the lack of accessible tools. Taking this into account, we developed Smell Pittsburgh, a system that enables community members to report odors and track where these odors are frequently concentrated. All smell report data are publicly accessible online. These reports are also sent to the local health department and visualized on a map along with air quality data from monitoring stations. This visualization provides a comprehensive overview of the local pollution landscape. Additionally, with these reports and air quality data, we developed a model to predict upcoming smell events and send push notifications to inform communities. We also applied regression analysis to identify statistically significant effects of push notifications on user engagement. Our evaluation of this system demonstrates that engaging residents in documenting their experiences with pollution odors can help identify local air pollution patterns, and can empower communities to advocate for better air quality. All citizen-contributed smell data are publicly accessible and can be downloaded from https://smellpgh.org.

This is the SECOND in a series of posts on applying Tim Ferriss' accelerated learning framework to Data Science. My goal is to become a world-class (top 5%) Data Scientist in 6 months, while open-sourcing everything I find & learn on the way. And if you stick around until the end, you're in for a special treat. A simple Google search of "how to learn Data Science" returns thousands of learning plans, degree programs, tutorials, and bootcamps. It's never been more difficult for a beginner to find signal in the noise. Everyone seems to have a different opinion, and the only common approach appears to be dumping a long list of courses to take and books to read, all the while providing little to no context into how these concepts fit into the bigger picture. This post is my attempt to convert all the buzzwords & fluffy terminology into explicitly-learnable skills.