The following is adapted from a joint release from the MIT Press and the Harvard Data Science Initiative. The MIT Press and the Harvard Data Science Initiative (HDSI) have announced the launch of the Harvard Data Science Review (HDSR). The open-access journal, published by MIT Press and hosted online via the multimedia platform PubPub, an initiative of the MIT Knowledge Futures group, will feature leading global thinkers in the burgeoning field of data science, making research, educational resources, and commentary accessible to academics, professionals, and the interested public. With demand for data scientists booming, HDSR will provide a centralized, authoritative, and peer-reviewed publishing community to service the growing profession. The first issue features articles on topics ranging from authorship attribution of John Lennon-Paul McCartney songs to machine learning models for predicting drug approvals to artificial intelligence (AI).

Gaurav Malhotra joins Scott Hanselman to show how you can run your Azure Machine Learning (AML) service pipelines as a step in your Azure Data Factory (ADF) pipelines. This enables you to run your machine learning models with data from multiple sources (85 data connectors supported in ADF). This seamless integration enables batch prediction scenarios such as identifying possible loan defaults, determining sentiment, and analyzing customer behavior patterns.

In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they require training from starch for a different related problem. In this work, we propose a transfer learning-based approach that significantly improves the performance of deep learning-based source code models. In contrast to traditional learning paradigms, transfer learning can transfer the knowledge learned in solving one problem into another related problem. First, we present two recurrent neural network-based models RNN and GRU for the purpose of transfer learning in the domain of source code modeling. Next, via transfer learning, these pre-trained (RNN and GRU) models are used as feature extractors. Then, these extracted features are combined into attention learner for different downstream tasks. The attention learner leverages from the learned knowledge of pre-trained models and fine-tunes them for a specific downstream task. We evaluate the performance of the proposed approach with extensive experiments with the source code suggestion task. The results indicate that the proposed approach outperforms the state-of-the-art models in terms of accuracy, precision, recall, and F-measure without training the models from scratch.

--Smart and agile drones are fast becoming ubiquitous at the edge of the cloud. The usage of these drones are constrained by their limited power and compute capability. In this paper, we present a Transfer Learning (TL) based approach to reduce on-board computation required to train a deep neural network for autonomous navigation via Deep Reinforcement Learning for a target algorithmic performance. A library of 3D realistic meta-environments is manually designed using Unreal Gaming Engine and the network is trained end-to- end. These trained meta-weights are then used as initializers to the network in a test environment and fine-tuned for the last few fully connected layers. V ariation in drone dynamics and environmental characteristics is carried out to show robustness of the approach. Using NVIDIA GPU profiler it was shown that the energy consumption and training latency is reduced by 3.7x and 1.8x respectively without significant degradation in the performance in terms of average distance traveled before crash i.e. The approach is also tested on a real environment using DJI T ello drone and similar results were reported. The video of the drone with proposed approach will be uploaded to Y ouTube. VER the past decade, Unmanned aerial vehicle (UA V) are emerging as a new form of IoT devices being used in varied applications such as reconnaissance, surveying, rescuing and mapping. Irrespective of the application, navigating autonomously is one of the key desirable features of UA Vs both indoors and outdoors.

What does it take to make the university the best learning experience in the lifecycle of one's education? Higher education is all about developing skills, exploring new theories, and applying them to the actualities of real life. Throughout this journey, students are encouraged to stay on top of their workload, study, and complete assessments all while simultaneously leading a healthy, active, and balanced social life. The essential materials relied on at university include books, books, and more books. As we move into an age of digitalization of practically everything, there is a reason to believe that the existing higher education model should too be digitalized to allow for an enhanced university experience.

New and creative uses of artificial intelligence are being developed every day. The potential of AI in education cannot be overstated. In edtech, the use of AI has flown largely under the radar thus far, but it has the potential to reimagine the student-teacher relationship and improve student outcomes across the board. Insights and predictions for the future of AI in education and in edtech from industry experts agree on several overarching trends. Technology, led by an interest in AI-based solutions, will produce a completely new educational system, and these are some of the trends I see impacting the work that is being done in the industry.

"This book provides a great practical guide to get started and execute on ML within a few days without necessarily knowing much about ML apriori. The first five chapters are enough to get you started and the next few chapters provide you a good feel of more advanced topics to pursue. A wonderful book for engineers who want to incorporate ML in their day-to-day work without necessarily spending an enormous amount of time going through a formal degree program."--Deepak Agarwal, VP of Artificial Intelligence at LinkedIn "This book is a great introduction to machine learning from a world-class practitioner and LinkedIn superstar Andriy Burkov. He managed to find a good balance between the math of the algorithms, intuitive visualizations, and easy-to-read explanations. This book will benefit the newcomers to the field as a thorough introduction to the fundamentals of machine learning, while the experienced professionals will definitely enjoy the practical recommendations from Andriy's rich experience in the field."--Karolis

For all the talk about how artificial intelligence could transform what happens in the classroom, AI hasn't yet lived up to the hype. AI involves creating computer systems that can perform tasks that typically require human intelligence. It's already being experimented with to help automate grading, tailor lessons to students' individual needs and assist English language learners. We heard about a few promising ideas at a conference I attended last week on artificial intelligence hosted by Teachers College, Columbia University. Shipeng Li, corporate vice president of iFLYTEK, talked about how the Chinese company is working to increase teachers' efficiency by individualizing homework assignments.

Economic intersectionality can refer to the compounded effects of any combination of characteristics associated with economic disadvantage. In this article, we focus on differing levels of automation-based challenges for African American men and women of various ages and education levels in rural and urban America. We project that African Americans in the 13 community archetypes we analyzed may have a higher rate of job displacement than workers in other segments of the US population due to rising automation and gaining a smaller share of the net projected job growth between 2017 and 2030. By 2030, the employment outlook for African Americans--particularly men, younger workers (ages 18–35), and those without a college degree--may worsen dramatically. Additionally, we find that African Americans are geographically removed from future job growth centers and more likely to be concentrated in areas of job decline.

Monitoring the right GPU performance metrics can go a long way in helping you train and deploy deep learning applications. GPU utilization is one of the primary metrics to observe during a deep learning training session. This metric is readily accessible through popular GPU monitoring interfaces such as NVIDIA's "NVIDIA-smi". A GPU's utilization is defined as the percentage of time one or more GPU kernels are running over the last second, which is analogous to a GPU being utilized by a deep learning program. Monitoring your deep learning training sessions' GPU utilization is one of the best indicators to determine if your GPU is actually being used. Moreover, monitoring the real-time utilization trend can help identify bottlenecks in your pre-processing and feature engineering pipelines that might be slowing down your training process.