Keras is a minimalist, highly modular neural networks library, written in Python and capable of running on top of either TensorFlow or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research. A model is understood as a sequence or a graph of standalone, fully-configurable modules that can be plugged together with as little restrictions as possible. In particular, neural layers, cost functions, optimizers, initialization schemes, activation functions, regularization schemes are all standalone modules that you can combine to create new models.

The AI analyzes student answers, and groups them based on similarity.

We have been hearing predictions for decades of a takeover of the world by artificial intelligence. In 1957, Herbert A. Simon predicted that within 10 years a digital computer would be the world's chess champion. That didn't happen until 1996. And despite Marvin Minsky's 1970 prediction that "in from three to eight years we will have a machine with the general intelligence of an average human being," we still consider that a feat of science fiction. The pioneers of artificial intelligence were surely off on the timing, but they weren't wrong; AI is coming.

Snapbooks--the Thinking Ink Press take on chapbooks--are short books packed with page-turning stories. Join us at Kaleid Gallery in San Jose on Friday, June 24, from 7:00-9:00 p.m. Marilyn and Anthony will read their work, and Keiko O'Leary will demonstrate and teach the art of hand-folding Instant Books from a single sheet of paper. You can also check out beautiful, original cover art created by local artist Sandi Billingsley for Thinking Ink Press. What: Launch party for Beyond the Fence and Sibling Rivalry When: Friday, June 24, 2016, from 7:00-9:00 p.m. Where: Kaleid Gallery 88 South Fourth Street, San Jose, CA, 95112, USA TEL: 1-408- 947-1785 Parking: Kaleid is located in downtown San Jose, on the street level of the Fourth Street parking garage (near the King Library). Garage parking costs 5 after 6:00 p.m. Street parking can be hard to find, but is free after 6:00 p.m. What Do I Need to Do?: Come to the party and bring friends!

There are elements of Apple's mobile and desktop operating systems that are getting a lot smarter with the upcoming release of iOS 10 and macOS Sierra right out of the gate. However, Apple also wants to make sure that its software keeps getting smarter, especially in things like iMessage, and that's where differential privacy comes in. With it, Apple can learn about the user without directly impacting privacy, by keeping what it learns, and what it still needs to learn, right on the device. In the end, this means that Apple can see its artificial intelligence, including Siri, get better without sacrificing privacy for the end user. As a result of all this, Recode wanted to get a few more bits of information ironed out, so it reached out to Apple to learn what it could.

Video Friday is your weekly selection of awesome robotics videos, collected by your nebulous Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next two months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. Tend.ai makes "cloud robotics for machine tending" a reality. Our system uses artificial intelligence powered by cloud computing to read machines' displays and press machines' buttons just like a human would.

Artificial intelligence may be the new face of medical diagnostics. For the first time, a flavor of A.I. called deep learning is being implemented in new ultrasound imaging equipment to aid in breast exams and help patients avoid unnecessary biopsies. A new feature in Samsung Medison's ultrasound system uses a deep-learning algorithm to make recommendations about whether a breast abnormality is benign or cancerous. The "S-Detect for Breast" feature is now included in an upgrade to the company's RS80A ultrasound system and is commercially available in parts of Europe, the Middle East and Korea and is pending FDA approval in the U.S., according to PR manager Doug Kim. Deep learning relies on large amounts of data to inform complex decision-making algorithms, has aided in everything from speech and image recognition software to pharmaceutical research.

Twitter is investing in machine learning with the 150 million acquisition of Magic Pony Technology, a London-based firm that developed machine learning techniques for visual processing. Calling machine learning "the core of everything we build at Twitter," CEO Jack Dorsey blogged that the buy builds on other investments his company has made: an acquisition of Madbits in July 2014 and Whetlab in June 2015. Machine learning makes it easier for Twitter users to create, share and discover "so that every time you open Twitter you're immersed in the most relevant news, stories, and events for you," he said. Magic Pony's team will join Twitter Cortex, a team of engineers, data scientists and machine learning researchers "dedicated to building a product in which people can easily find new experiences to share and participate in." Twitter has 310 monthly active users and 3,800 employees.

Optimization for machine learning is essential to ensure that data mining models can learn from training data in order to generalize to future test data. Data mining models can have millions of parameters that depend on the training data and, in general, have no analytic definition. In such cases, effective models with good generalization capabilities can only be found by using optimization strategies. Optimization algorithms come in all shapes and sizes, just like anything in life. Attempting to create a single optimization algorithm for all problems would be as foolhardy as seeking to create a single motor vehicle for all drivers --there is a reason we have semi-trucks, automobiles, motorcycles, etc.

Ask most people outside academia or Silicon Valley what comes to mind when they hear the term "machine learning" and you're likely to get a response that involves a movie like "The Matrix" or "Ex Machina." You're less likely to hear how it's a great tool for fraud detection or supply chain optimization, and that's too bad. Machine learning has a tremendous range of business applications, from optimizing data centers to predicting fine wine price changes to retail market basket analysis. With that in mind, I hope to cut through the science fiction clutter and misconceptions so you can consider how machine learning relates to your business. Many have heard about Andrew Ng's popular graduate level machine learning course at Stanford, now available on Coursera.