Goto

Collaborating Authors

School Nutrition


The 5 best deals and sales you can shop this Tuesday

USATODAY - Tech Top Stories

Tuesday's best early Black Friday deals on Amazon are on some of the most popular holiday gifts. If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. Coming back from a long weekend is always hard, especially one that's so close to the holidays, like Veteran's Day. If you're just settling back into the office, chances are you could use a few distractions, and lucky for you, we've got five of them--specifically in the form of these great deals you can snag on Amazon.


Decoding Regulations Using Machine Learning (sponsored by IBM) - Dinesh Nirmal (IBM)

#artificialintelligence

IBM Analytics's Dinesh Nirmal solves school lunch and the struggle to keep ahead of regulations. Follow O'Reilly on: Twitter: http://twitter.com/oreillymedia


Fairness Under Composition

arXiv.org Machine Learning

Much of the literature on fair classifiers considers the case of a single classifier used once, in isolation. We initiate the study of composition of fair classifiers. In particular, we address the pitfalls of na{\i}ve composition and give general constructions for fair composition. Focusing on the individual fairness setting proposed in [Dwork, Hardt, Pitassi, Reingold, Zemel, 2011], we also extend our results to a large class of group fairness definitions popular in the recent literature. We exhibit several cases in which group fairness definitions give misleading signals under composition and conclude that additional context is needed to evaluate both group and individual fairness under composition.


The Web's Recommendation Engines Are Broken. Can We Fix Them?

WIRED

Today, recommendation engines are perhaps the biggest threat to societal cohesion on the internet--and, as a result, one of the biggest threats to societal cohesion in the offline world, too. The recommendation engines we engage with are broken in ways that have grave consequences: amplified conspiracy theories, gamified news, nonsense infiltrating mainstream discourse, misinformed voters. Recommendation engines have become The Great Polarizer. Ironically, the conversation about recommendation engines, and the curatorial power of social giants, is also highly polarized. A creator showed up at YouTube's offices with a gun last week, outraged that the platform had demonetized and downranked some of the videos on her channel.


The news that made us smile this week

BBC News

Everyone needs a distraction now and then, so here are some things we spotted in the news that put a little smile on our faces this week. We hope they do the same to you. Former US First Lady Michelle Obama met, and danced with, two-year-old Parker Curry this week. Parker went viral after her mum posted a photograph of her mesmerised by Mrs Obama's official painting. "Maybe one day I'll proudly look up at a portrait of you," the former first lady wrote on Twitter.


PyData New York City 2017 - YouTube

@machinelearnbot

Keynote: Kerstin Kleese van Dam - Enabling Real Time Analysis & Decision Making Keynote: Thomas Sargent - Economic Models Keynote: Andrew Gelman - Data Science Workflow Andrew Therriault - Learning in Cycles: Implementing Sustainable Machine Learning Models... Jeff Reback - What is the Future of Pandas Chalmer Lowe - Pandas and Date Time Steve Dower - Why does Python need security transparency? Sudheesh Katkam - Simplifying And Accelerating Data Access for Python With Dremio and Apache Arrow Casey Clements - Money for Nothing Introducing Pennies, an Open Source Pythonic Pricing Package Noemi Derzsy - Data Science Keys to Open Up OpenNASA Datasets Tyler A. Erickson - Analyzing Petabytes of Earth Science Data with Jupyter and Earth Engine Nicole Carlson - Turning PyMC3 into scikit learn Leon Yin - Reverse image search engines using out of the box machine learning libraries Keith Ingersoll - Jupyter, R Shiny, and the Data Science Web App Landscape Ami Tavory - Getting Scikit Learn To Run ...


SHOPPER: A Probabilistic Model of Consumer Choice with Substitutes and Complements

arXiv.org Machine Learning

We develop SHOPPER, a sequential probabilistic model of market baskets. SHOPPER uses interpretable components to model the forces that drive how a customer chooses products; in particular, we designed SHOPPER to capture how items interact with other items. We develop an efficient posterior inference algorithm to estimate these forces from large-scale data, and we analyze a large dataset from a major chain grocery store. We are interested in answering counterfactual queries about changes in prices. We found that SHOPPER provides accurate predictions even under price interventions, and that it helps identify complementary and substitutable pairs of products.


Accenture Labs and Akshaya Patra Use Disruptive Technologies to Enhance Efficiency in Mid-Day Meal Program for School Children

#artificialintelligence

Accenture Labs and Akshaya Patra Use Disruptive Technologies to Enhance Efficiency in Mid-Day Meal Program for School Children "Million Meals" project applied artificial intelligence, the Internet of Things and blockchain to drive efficiency and timeliness of lunch program in government schools across India BENGALURU, India; Apr. 20, 2017 – Accenture (NYSE: ACN) and Akshaya Patra, the world's largest NGO-run Mid-Day Meal Program, collaborated on an innovative project that used disruptive technologies to exponentially increase the number of meals served to children in schools in India that are run and aided by the government. The "Million Meals" project revolutionized Akshaya Patra's supply chain and operations, resulting in improved food quality and expanded service reach. Rooted in a vision to eliminate child hunger, the "Million Meals" project demonstrated how disruptive technologies such as artificial intelligence (AI), the Internet of Things (IoT) and blockchain can help address significant challenges in mass meal production and delivery. Accenture Labs, the research and development arm of Accenture, executed the project over a period of six months in Akshaya Patra's Bengaluru kitchen. An analysis of the project indicated a potential to improve efficiency by 20 percent, which could boost the number of meals served by millions.


Meet BIG-i, the 'first personalised household robot'

Daily Mail - Science & tech

The concept of a robot assistant in the home is moving from sci-fi to reality thanks to a new product that claims to be the first personalised household robot. BIG-i is able to interpret voice commands and perform simple household tasks, such as controlling other smart devices and providing reminders. NXROBO, the company behind the robot, believes that in the future every family will have a robot which will act as the'hub for all smart home appliances.' BIG-i is a natural-interaction robot with mobility, 3D vision, voice programming, and active perception. The robot, which stands 2ft 6ins (80 centimetres) tall, is able to move freely around the home as necessary, avoiding obstacles and can be controlled via a smartphone app as well as voice commands. It also has facial recognition technology that allows it to recognise family and friends in order to carry out specific tasks, such as reminding the children to remember their school lunchbox before they leave the house.


Tuesday's TV highlights: 'Cosplay Melee' on Syfy

Los Angeles Times

The Flash Continuing a crossover storyline that started on "Supergirl," Barry (Grant Gustin) and his team are taken aback when Mon-El and Hank Henshaw (guest stars Chris Wood and David Harewood, respectively) appear on their Earth with Supergirl (Melissa Benoist), who is comatose after the Music Meister's (guest star Darren Criss) attack in this new episode. New Girl Jess (Zooey Deschanel) uses her time taking care of her dad (guest star Rob Reiner) as an excuse to avoid thinking about her feelings for Nick (Jake Johnson), while Nick panics about his relationship with Reagan (Megan Fox). The Mick When Mickey (Katilin Olsen) figures out that Chip (Thomas Barbusca) is getting scammed by a girl he met online, she gives him a crash course in how to be a wolf, not a sheep, in life. A second new episode follows at 9:30. DC's Legends of Tomorrow In France during World War I, the Legends -- on a mission to retrieve the last remaining fragments of the Spear of Destiny -- enlist the help of a soldier named John Ronald Reuel Tolkien (guest star Jack Turner) and find their search is leading them to the front lines.