Einstein once said that if you judge a fish by its ability to climb a tree, it'll live its whole life thinking it's stupid. What you may not know is that he was referring to the public educational system and the one size fits all approach to teaching. Although more than a century passed since he said this, traditional models of education still exist till this day and still insist on standardized teaching techniques, despite their inability to deliver the best results. More and more learners -- in the academic and business world -- don't find these models challenging and engaging, so they're searching for alternatives, they want more personalized learning experiences. Personalized learning is the tailoring of learning environments with the primary focus on learners and how they experience the process of knowledge acquisition.

A few months ago I had the opportunity to complete Andrew Ng's Machine Learning MOOC taught on Coursera. It serves as a very good introduction for anyone who wants to venture into the world of AI/ML. I always wondered how amazing this course could be if it were in Python. I finally decided to re-take the course but only this time I would be completing the programming assignments in Python. In these series of blog posts, I plan to write about the Python version of the programming exercises used in the course.

Kalman filter is a key tool for time-series forecasting and analysis. We show that the dependence of a prediction of Kalman filter on the past is decaying exponentially, whenever the process noise is non-degenerate. Therefore, Kalman filter may be approximated by regression on a few recent observations. Surprisingly, we also show that having some process noise is essential for the exponential decay. With no process noise, it may happen that the forecast depends on all of the past uniformly, which makes forecasting more difficult. Based on this insight, we devise an on-line algorithm for improper learning of a linear dynamical system (LDS), which considers only a few most recent observations. We use our decay results to provide the first regret bounds w.r.t. to Kalman filters within learning an LDS. That is, we compare the results of our algorithm to the best, in hindsight, Kalman filter for a given signal. Also, the algorithm is practical: its per-update run-time is linear in the regression depth.

The 5 courses in this University of Michigan specialization introduce learners to data science through the python programming language. This skills-based specialization is intended for learners who have a basic python or programming background, and want to apply statistical, machine learning, information visualization, text analysis, and social network analysis techniques through popular python toolkits such as pandas, matplotlib, scikit-learn, nltk, and networkx to gain insight into their data. Introduction to Data Science in Python (course 1), Applied Plotting, Charting & Data Representation in Python (course 2), and Applied Machine Learning in Python (course 3) should be taken in order and prior to any other course in the specialization. After completing those, courses 4 and 5 can be taken in any order. All 5 are required to earn a certificate.

On a balmy summer's day in San Francisco, Milena Marinova is sitting on the roof terrace of the offices of Pearson, a company in the midst of a radical transformation from publishing powerhouse to digital-education platform, wrapped in a gray shawl and explaining how she plans to build advanced, deep-learning algorithms that could educate the next generation of students. This is no easy task. With millions of students using its education-software, Pearson has amassed "terrabytes" of data from student homework and even textbooks that have been digitized, data that Marinova is now pulling together to build software that can automatically give students feedback on their work like a teacher would. Instead of just telling them that an answer is right or wrong, a future update to Pearson's math homework tool will give more detailed feedback on how they went wrong in the steps taken to get an answer, Marinova told Forbes in an interview. Pearson is starting with math because the topic is relatively easy to structure and digitize.

We present a unified framework for Batch Online Learning (OL) for Click Prediction in Search Advertisement. Machine Learning models once deployed, show non-trivial accuracy and calibration degradation over time due to model staleness. It is therefore necessary to regularly update models, and do so automatically. This paper presents two paradigms of Batch Online Learning, one which incrementally updates the model parameters via an early stopping mechanism, and another which does so through a proximal regularization. We argue how both these schemes naturally trade-off between old and new data. We then theoretically and empirically show that these two seemingly different schemes are closely related. Through extensive experiments, we demonstrate the utility of of our OL framework; how the two OL schemes relate to each other and how they trade-off between the new and historical data. We then compare batch OL to full model retrains, and show how online learning is more robust to data issues. We also demonstrate the long term impact of Online Learning, the role of the initial Models in OL, the impact of delays in the update, and finally conclude with some implementation details and challenges in deploying a real world online learning system in production. While this paper mostly focuses on application of click prediction for search advertisement, we hope that the lessons learned here can be carried over to other problem domains.

To learn Chinese in this room, talk to the floating panda head. The Mandarin-speaking avatar zips around a 360-degree restaurant scene in an artificial intelligence-driven instruction program that looks like a giant video game. Rensselaer Polytechnic Institute students testing the technology move inside the 12-foot-high, wrap-around projection to order virtual bean curd from the panda waiter, chat with Beijing market sellers and practice tai chi by mirroring moves of a watchful mentor. "Definitely less anxiety than messing it up with a real human being," says Rahul Divekar, a computer science graduate student working on the project. "So compared to that anxiety, this is a lot more easy."

Abstract--Increasingly fast development and update cycle of online course contents, and diverse demographics of students in each online classroom, make student performance prediction in real-time (before the course finishes) an interesting topic for both industrial research and practical needs. In that, we tackle the problem of real-time student performance prediction with ongoing courses in a domain adaptation framework, which is a system trained on students' labeled outcome from one previous coursework but is meant to be deployed on another. In particular, we first review recently-developed GritNet architecture [1] which is the current state of the art for student performance prediction problem, and introduce a new unsupervised domain adaptation method to transfer a GritNet trained on a past course to a new course without any (students' outcome) label. Our results for real Udacity students' graduation predictions show that the GritNet not only generalizes well from one course to another across different Nanodegree programs, but enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging. With the growing need for people to keep learning throughout their careers, massive open online course (MOOCs) companies, such as Udacity and Coursera, not only aggressively design new courses that are relevant (e.g., self-driving cars and flying cars) but refresh existing courses' content frequently to keep them up-to-date.

In modern computer science education, massive open online courses (MOOCs) log thousands of hours of data about how students solve coding challenges. Being so rich in data, these platforms have garnered the interest of the machine learning community, with many new algorithms attempting to autonomously provide feedback to help future students learn. But what about those first hundred thousand students? In most educational contexts (i.e. classrooms), assignments do not have enough historical data for supervised learning. In this paper, we introduce a human-in-the-loop "rubric sampling" approach to tackle the "zero shot" feedback challenge. We are able to provide autonomous feedback for the first students working on an introductory programming assignment with accuracy that substantially outperforms data-hungry algorithms and approaches human level fidelity. Rubric sampling requires minimal teacher effort, can associate feedback with specific parts of a student's solution and can articulate a student's misconceptions in the language of the instructor. Deep learning inference enables rubric sampling to further improve as more assignment specific student data is acquired. We demonstrate our results on a novel dataset from Code.org, the world's largest programming education platform.

On a balmy summer's day in San Francisco, Milena Marinova is sitting on the roof terrace of the offices of Pearson, a company in the midst of a radical transformation from publishing powerhouse to digital-education platform, wrapped in a gray shawl and explaining how she plans to build advanced, deep-learning algorithms that could educate the next generation of students. This is no easy task. With millions of students using its education-software, Pearson has amassed "terrabytes" of data from student homework and even textbooks that have been digitized, data that Marinova is now pulling together to build software that can automatically give students feedback on their work like a teacher would. Instead of just telling them that an answer is right or wrong, a future update to Pearson's math homework tool will give more detailed feedback on how they went wrong in the steps taken to get an answer, Marinova told Forbes in an interview. Pearson is starting with math because the topic is relatively easy to structure and digitize.