If you want to know what motivated me to create TrueShelf (an AI powered adaptive learning platform) and the future of learning, please read my interview on Edsurge.
As some of you know, I am now the Founder & CEO of TrueShelf Inc, an EdTech startup based in the Bay Area. TrueShelf is aimed at developing platform, content and products to aid intuitive, visual, social, adaptive and personalized learning. TrueShelf consists of two main components: TrueShelf Online Network and TrueShelf Apps. Read our FAQ for more details.
Today’s post is about TrueShelf apps, intuitive and visual learning apps that are carefully designed to help students learn specific concepts in a systematic and adaptive manner.
Recently we released our True Vocabulary app, our first adaptive learning app. The existing solutions to learn english vocabulary are either too hard-to-use and/or expensive and/or old-fashioned (e.g. flashcards). Our app is focused primarily on automatic personalization and ease-of-use. It has already received more than 25,000 downloads on the iOS app store. If you are preparing for GRE, SAT, GMAT, ACT, CAT or simply interested in improving your english vocabulary, True Vocabulary app provides an efficient and elegant step by step adaptive learning process. It is an intelligent personalized vocabulary tutor.
True Vocabulary uses an intelligent algorithm (based on the concepts of spaced repetition, Leitner system and lexical cohesion) to design adaptive multiple-choice vocabulary quizzes. Learning tasks are divided into small sets of multiple-choice quizzes designed to help you master the basic words before moving on to the advanced words. Words closely related to your hardest words are selected more frequently in the quizzes. For a fixed word, the correct and wrong answers are selected adaptively giving rise to hundreds of combinations. After each wrong answer, you receive a detailed feedback with the meaning and usage of the corresponding word. Coins, Gems and Levels are unlocked adaptively to motivate, evaluate and reward the learner.
This is just the beginning of our journey to make education elegant, efficient and painless for hundreds of thousands of students and teachers. In future posts, I will talk more about TrueShelf’s vision and roadmap. Stay tuned.
Today’s post is about the following paper, a joint work with Qiuyi Zhang, one of my advisees. Qiuyi Zhang is now a graduate student in the Mathematics department of Berkeley.
- Shiva Kintali, Qiuyi Zhang. Forbidden Directed Minors and Directed Pathwidth. (Preprint is available on my publications page)
Undirected graphs of pathwidth at most one are characterized by two forbidden minors i.e., (i) the complete graph on three vertices and (ii) the spider graph with three legs of length two each (see the following figure).
Directed pathwidth is a natural generalization of pathwidth to digraphs. We proved that digraphs of directed pathwidth at most one are characterized by a finite number of forbidden directed minors. In particular, we proved that the number of vertices in any forbidden directed minor is at most 8*160000+7. Ahem !!
This paper falls in the “directed minors” part of my research interests. In an earlier theorem, proved in April 2013 (see this earlier post), we proved that partial 1-DAGs are characterized by three forbidden directed minors. In a similar vein, I conjectured that the digraphs with directed pathwidth at most 1 are characterized by a finite number of forbidden directed minors. I assumed that the number of forbidden directed minors is number is around 100. So we started this project in May 2013 and started making a list of carefully constructed forbidden directed minors and tried to extend our techniques from partial 1-DAGs. Here is an initial list of minors we found.
All the forbidden minors we found, looked very cute and we assumed that a proof is nigh. Soon, we realized that the list is growing quickly and none of our earlier techniques are applicable. After almost an year of patient efforts and roller coaster rides, we proved our finiteness theorem in May 2014, two weeks before Qiuyi Zhang’s thesis defense. It took us 10 more months to get the paper to its current status. So this is a two year long adventure.
I am hoping to prove more theorems in the “directed minors” area in the coming years. The current paper taught me that patience and focus are big factors to make consistent progress. There should be a nice balance between `proving new theorems’ and `writing up the existing results’.
Today’s blog post is a quick announcement of “personalization” feature in Polytopix. We added a new feature that allows users to add their (possibly multiple) twitter accounts in Polytopix. The user’s twitter stream is used to personalize and rank the news articles on Polytopix. More importantly, our semantic similarity algorithms will display contextual explanatory articles along-side the news articles in the user’s feed.
On popular demand, we added a new feature called “weekly news digest” in Polytopix. Our ranking algorithm picks the top (at most 10) news articles (along with the contextual explanatory articles) from the last one week and emails them every Friday midnight. I will post the details of our ranking algorithm in a future blog post.
If you want to receive this weekly digest, subscribe on polytopix.com
Here is an example from the week 01/24/2015 – 01/30/2015