Click here to skip the intro and dive right in! When I started the residency program in the summer of 2017, I had a lot of experience programming, and a good understanding of machine learning, but I had never used Tensorflow before. I figured that given my background I'd be able to pick it up quickly. To my surprise, the learning curve was fairly steep, and even months into the residency, I would occasionally find myself confused about how to turn ideas into Tensorflow code. I'm writing this blog post as a message-in-a-bottle to my former self: it's the introduction that I wish I had been given before starting on my journey. Hopefully, it will also be a helpful resource for others. In the three years since its release, Tensorflow has cemented itself as a cornerstone of the deep learning ecosystem.

We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning. We show that an approximate version of the bilevel problem can be solved by taking into explicit account the optimization dynamics for the inner objective. Depending on the specific setting, the outer variables take either the meaning of hyperparameters in a supervised learning problem or parameters of a meta-learner. We provide sufficient conditions under which solutions of the approximate problem converge to those of the exact problem. We instantiate our approach for meta-learning in the case of deep learning where representation layers are treated as hyperparameters shared across a set of training episodes. In experiments, we confirm our theoretical findings, present encouraging results for few-shot learning and contrast the bilevel approach against classical approaches for learning-to-learn.

Ever wondered how an Internet search engine - Google, Yahoo! or Bing - fetches you the correct information in seconds? Or, Amazon fishes out the product you've been looking for in a jiffy? Or, the food delivery app knows so much about restaurants across the country? Well, all these Internet engines run on the same oil: data. More specifically, they look for patterns in a deluge of data to produce the best results for your queries within a fraction of a second.

Firstly, Karen Baker and Martin McGovern from Udacity help organize and facilitate this AMA for the life long learners at Udacity. I am deeply thankful to Karen, Martin and Udacity for this opportunity to share the knowledge. QQ: What is the best piece of advice you've ever received in your career? VK: I have got some good advice from books as well as mentors. QQ: What suggestions do you have around building your portfolio?

Record and run settings a team which includes 2 Stanford-educated, ex-Googlers and 2 ex-Flipkart Lead Analysts. This team has decades of practical experience in working with large-scale data processing jobs. Relational Databases are so stuffy and old! Welcome to HBase – a database solution for a new age. HBase: Do you feel like your relational database is not giving you the flexibility you need anymore?

Pearson is concentrating efforts in the area of artificial intelligence (AI) and has hired a former Intel executive, Milena Marinova, to be its senior vice president for AI products and solutions. The appointment has been described as "first of its kind" for the education industry. Marinova, who was previously senior director of AI Solutions for Intel's Artificial Intelligence Products Group, will act as a spokesperson for the role of AI in education while spearheading "the digital and AI transformation of Pearson". At Intel, Marinova led the development for commercial applications of AI across various industries, including Internet of Things, robotics and AR/VR, and advised Intel Capital on investments in these areas. She also previously held executive roles at Idealab, a startup incubator, and Hyundai Capital America.

Students work on computers in Henderson, Nev. Several states including Utah and Ohio use automated grading on student essays written as part of standardized tests. Students work on computers in Henderson, Nev. Several states including Utah and Ohio use automated grading on student essays written as part of standardized tests. B: They can be scored quickly. C: They score without human bias.

AI has an important role to play in the education industry, which also happens to be a lucrative and still–growing space. The global private tutoring market alone will be worth more than $102 billion by the end of this year, and public education offers an equally fruitful opportunity. AI-powered music tutoring app Tonara today announced the launch of its Tonaro 360 music tutoring service, along with a new music store. Throughout beta testing, music teachers reported up to a 68 percent increase in practice hours among students using Tonara 360. So how does it work?

Transfer learning has achieved promising results by leveraging knowledge from the source domain to annotate the target domain which has few or none labels. Existing methods often seek to minimize the distribution divergence between domains, such as the marginal distribution, the conditional distribution or both. However, these two distances are often treated equally in existing algorithms, which will result in poor performance in real applications. Moreover, existing methods usually assume that the dataset is balanced, which also limits their performances on imbalanced tasks that are quite common in real problems. To tackle the distribution adaptation problem, in this paper, we propose a novel transfer learning approach, named as Balanced Distribution \underline{A}daptation~(BDA), which can adaptively leverage the importance of the marginal and conditional distribution discrepancies, and several existing methods can be treated as special cases of BDA. Based on BDA, we also propose a novel Weighted Balanced Distribution Adaptation~(W-BDA) algorithm to tackle the class imbalance issue in transfer learning. W-BDA not only considers the distribution adaptation between domains but also adaptively changes the weight of each class. To evaluate the proposed methods, we conduct extensive experiments on several transfer learning tasks, which demonstrate the effectiveness of our proposed algorithms over several state-of-the-art methods.

Extracting significant places or places of interest (POIs) using individuals' spatio-temporal data is of fundamental importance for human mobility analysis. Classical clustering methods have been used in prior work for detecting POIs, but without considering temporal constraints. Usually, the involved parameters for clustering are difficult to determine, e.g., the optimal cluster number in hierarchical clustering. Currently, researchers either choose heuristic values or use spatial distance-based optimization to determine an appropriate parameter set. We argue that existing research does not optimally address temporal information and thus leaves much room for improvement. Considering temporal constraints in human mobility, we introduce an effective clustering approach - namely POI clustering with temporal constraints (PC-TC) - to extract POIs from spatio-temporal data of human mobility. Following human mobility nature in modern society, our approach aims to extract both global POIs (e.g., workplace or university) and local POIs (e.g., library, lab, and canteen). Based on two publicly available datasets including 193 individuals, our evaluation results show that PC-TC has much potential for next place prediction in terms of granularity (i.e., the number of extracted POIs) and predictability.