Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection. This work proposes a simple technique for addressing this issue: use a data-efficient content selector to over-determine phrases in a source document that should be part of the summary. We use this selector as a bottom-up attention step to constrain the model to likely phrases. We show that this approach improves the ability to compress text, while still generating fluent summaries. This two-step process is both simpler and higher performing than other end-to-end content selection models, leading to significant improvements on ROUGE for both the CNN-DM and NYT corpus. Furthermore, the content selector can be trained with as little as 1,000 sentences, making it easy to transfer a trained summarizer to a new domain.

Last week Rohit Singh and Alberto Nieto hosted a GeoDev Webinar on "Integrating Deep Learning with ArcGIS Using Python". We had a lot of great questions come out of the webinar and will be updating this post to add the Q&A that were not addressed during the webinar. Many viewers requested to have access to the PowerPoint presentation, and the presenters were more than happy to share. In their presentation, they offered access to their demos and resources that may be helpful for those developing in Python. Did you miss the webinar?

Machine learning systems can be trained to recognize emotional expressions from images of human faces, with a high degree of accuracy in many cases. Image by Tsukiko Kiyomidzu However, implementation can be a complex and difficult task. The technology is at a relatively early stage. High quality datasets can be hard to find. And there are various pitfalls to avoid when designing new systems. This article provides an introduction to the field known as Facial Expression Recognition (FER).

Our online personality is now as measurable as our carbon footprint. In addition to some rather obvious statistics, such as how often we tweet, how many others we follow, and how many others follow us, we principally reveal ourselves in our choice of words. How often I refer to "I," "me," "myself," "mine," and "my" can tell you a good deal about my propensity for self-absorption, while a frequent use of "we" and "our" indicates a willingness to share either credit or blame. The frequency with which I use "you" or "your" is just as indicative of a desire to channel my feelings outward, so if I also show a partiality for negative words, this pairing of observables is strongly indicative of hostility. Frequent use of "LOL," "OMG," and the exclamation point reveals an excitable personality, while emoticons and hashtags such as #irony and #sarcasm make explicit not just my feelings but a playful stance toward the content of my own tweets. The use of complex sentence structures hinging on the logical connectives "if," "but," "yet," and "therefore" suggests a capacity for analytical thinking, while frequent questions--especially those involving words of negative sentiment--offer a clue to a nervous disposition.

Dopamine Dopamine is a research framework for fast prototyping of reinforcement learning algorithms. Simple Baselines for Human Pose Estimation and Tracking The project is an official implement of Microsoft ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking"

Special purpose object detection systems need to be fast, accurate and dedicated to classifying a handful but relevant number of objects. Our aim was to integrate a system which utilizes the Inception's vast heuristically mapped image pre-diction tree along-with a real time system accurate and robust enough to work at various processing powers and give the user enough confidence of identifying and detecting object with a single frame. As this property can be utilized at huge number of places relying on real time detection, it might not be limited to only driving assistance or autonomous driving systems, but are beyond the scope of this project. To come up with a novel dataset, which would have an image tree with enough weights and variety so as to predict the objects being identified with high accuracy and precision, was taken up to set up the softmax layer of Inception, which was earlier weighted by the existing ImageNet dataset. The results were a convincing recognition accuracy and prediction confidence with real time test frames of a video.

A new form of misinformation is poised to spread through online communities as the 2018 midterm election campaigns heat up. Called "deepfakes" after the pseudonymous online account that popularized the technique – which may have chosen its name because the process uses a technical method called "deep learning" – these fake videos look very realistic. So far, people have used deepfake videos in pornography and satire to make it appear that famous people are doing things they wouldn't normally. But it's almost certain deepfakes will appear during the campaign season, purporting to depict candidates saying things or going places the real candidate wouldn't. Because these techniques are so new, people are having trouble telling the difference between real videos and the deepfake videos.

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.

Last year, China's government put out its plan to lead the world in AI by 2030. As Eric Schmidt has explained, "It's pretty simple. By 2020, they will have caught up. By 2025, they will be better than us. By 2030, they will dominate the industries of AI."

Although the idea of vehicle detection is not a groundbreaking one and has been around since the emergence of video cameras and embedded sensors, these methods were often marred by high capital and maintenance costs and a high complexity from having to integrate multiple data sources, each with a limited band of inputs. The prevalence of drones in the commercial market in recent years on the other hand, has brought about a new era of state-of-the-art aerial photogrammetry and a drastic reduction in the cost of obtaining aerial data. With this sudden increase in information, and by combining machine learning with GIS technologies, we are now capable of performing new and insightful analyses on issues of interest. Existent business problems which stand to benefit from this include customer flow analyses and demographic modelling. This is particularly useful for those in the retail sector looking to monitor peak business hours by counting the number of parked vehicles at a given time and also extrapolate useful customer information (such as income, marital status, household size and even political inclination) by classifying the types of vehicles they own.